© 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. 26818
    Prev
    Next
    INDEX
    Explanations

    life, song, creation, eyes, words, stage, threatened

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

    SQL auto increment primary key

    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
     incógn
    0.52
    initial
    0.46
    󠁢
    0.46
     إِل
    0.44
    the
    0.44
    establishment
    0.43
     گھ
    0.42
     بِ
    0.42
    h
    0.42
     Rie
    0.41
    POSITIVE LOGITS
    也没有
    0.45
    র্যের
    0.44
    也沒有
    0.43
     burying
    0.39
     цих
    0.39
    你也
    0.38
    也没
    0.38
    nière
    0.37
     सेल्फी
    0.37
    哦
    0.37
    Activations Density 0.000%

    No Known Activations