© 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. 175633
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation or common determiners

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

    of sexual assault or theft

    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
    icycles
    0.52
    Analysts
    0.44
    ミ
    0.44
     الوزراء
    0.44
    quipe
    0.43
    媳
    0.43
    ケン
    0.42
     Analysts
    0.42
    加快
    0.42
    AAE
    0.41
    POSITIVE LOGITS
     cusp
    0.51
     comparison
    0.48
     deflate
    0.46
    ",[(
    0.45
     비교
    0.45
     boton
    0.45
    زیز
    0.45
     meadows
    0.44
    зию
    0.44
    ']['
    0.44
    Activations Density 0.000%

    No Known Activations