© 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. 34391
    Prev
    Next
    INDEX
    Explanations

    code-like syntax or structure

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     when
    -1.27
     and
    -1.24
    vartis
    -1.21
    hiva
    -1.17
     after
    -1.17
    cún
    -1.15
     térm
    -1.13
     during
    -1.12
    thodox
    -1.06
     some
    -1.03
    POSITIVE LOGITS
    usually
    1.30
    brought
    1.20
    perhaps
    1.20
    moved
    1.16
    wouldn
    1.13
    previously
    1.13
    都没
    1.12
    called
    1.11
    generally
    1.10
    took
    1.09
    Activations Density 0.001%

    No Known Activations