© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6067
    Prev
    Next
    INDEX
    Explanations

    common continuations after words

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

    gained electrons, individual liberties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zhang
    0.36
     PLHIV
    0.35
     dieser
    0.34
     siRNA
    0.34
     Σ
    0.34
     the
    0.33
     idempotent
    0.33
     this
    0.33
     instantiate
    0.33
     PoE
    0.31
    POSITIVE LOGITS
    िति
    0.34
     Джор
    0.31
     جور
    0.31
     със
    0.30
     முதல்
    0.30
    ڠ
    0.29
    ംഗ
    0.29
    печа
    0.29
    alleng
    0.28
     खूबसूरत
    0.28
    Activations Density 0.242%

    No Known Activations