© 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. 137568
    Prev
    Next
    INDEX
    Explanations

    reason for, factors for, business, coffee and, city rules, are no, Dutch, below, attempted insurance, four seasons

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

    just comparisons or specific words

    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
     that
    0.58
    that
    0.57
    ją
    0.45
    مین
    0.44
    ین
    0.43
     që
    0.43
    ജ
    0.43
     guaranteeing
    0.42
     কারণেই
    0.42
     engineers
    0.41
    POSITIVE LOGITS
     =\
    0.49
    )/\
    0.49
     *)
    0.49
    …………
    0.47
    BID
    0.47
    ;\
    0.47
     ……
    0.47
    FIND
    0.47
     \
    0.46
     ::=
    0.46
    Activations Density 0.000%

    No Known Activations