© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73034
    Prev
    Next
    INDEX
    Explanations

    findings revealed after analysis

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on verbs and phrases that introduce reported experimental results or findings (e.g. “revealed,” “demonstrated,” “showed”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -1.70
     borealis
    -1.30
    🧌
    -1.25
     you
    -1.24
    tiendo
    -1.23
    OpenHelper
    -1.22
     दौरान
    -1.20
     moléculas
    -1.19
    ólica
    -1.18
     CascadeType
    -1.17
    POSITIVE LOGITS
     that
    1.95
     a
    1.70
     the
    1.44
    ようだ
    1.18
     no
    1.17
     also
    1.13
     significant
    1.12
     Minuten
    1.10
    indicates
    1.09
    three
    1.09
    Activations Density 0.078%

    No Known Activations