© 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. 7023
    Prev
    Next
    INDEX
    Explanations

    limiting responses with only

    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
     A
    2.11
     how
    2.10
     from
    2.10
    <u>
    2.01
    zenia
    1.99
     How
    1.99
    端的
    1.96
     gesamte
    1.95
     From
    1.94
    from
    1.93
    POSITIVE LOGITS
     intermittently
    1.91
     sporadically
    1.90
     detectable
    1.87
    \,.
    1.86
    *********
    1.83
     vaguely
    1.80
     faintly
    1.80
     reluctantly
    1.79
     \,.
    1.79
     existent
    1.78
    Activations Density 0.079%

    No Known Activations