© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4691
    Prev
    Next
    INDEX
    Explanations

    face etched with stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    /
    1.60
     nhé
    1.52
    /?
    1.51
     PLEASE
    1.46
     plz
    1.45
     please
    1.41
    ?
    1.39
     estos
    1.38
    _
    1.36
     =
    1.35
    POSITIVE LOGITS
    reinforced
    1.61
    ructured
    1.56
    ANNOT
    1.51
     handicrafts
    1.51
    geschoss
    1.49
     crippled
    1.48
    耄
    1.47
    quered
    1.43
    $-,
    1.43
    acariy
    1.42
    Activations Density 0.107%

    No Known Activations