© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 64103
    Prev
    Next
    INDEX
    Explanations

    Another context

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

    The neuron is keyed to salient “signal” verbs—present‐tense action words that introduce or enumerate main points (e.g. learn, reach, include, use, comes, calling).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     głównie
    -1.49
     därför
    -1.46
     ilyen
    -1.40
    _
    -1.28
    وقال
    -1.25
     säkert
    -1.24
     várias
    -1.19
    íteni
    -1.18
    際は
    -1.17
     hlavně
    -1.17
    POSITIVE LOGITS
     another
    3.41
     something
    2.97
    另一个
    2.33
    Another
    2.33
    another
    2.23
    另一
    2.22
    something
    2.08
     دیگری
    2.06
    另一种
    1.98
    另一個
    1.97
    Activations Density 0.200%

    No Known Activations