© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1033
    Prev
    Next
    INDEX
    Explanations

    what can be offered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     trataro
    2.49
    fnamefont
    2.46
     HTMLSc
    2.40
     ServicePolicy
    2.39
     BlackSholes
    2.38
    뺻
    2.35
    zoomSeekBar
    2.34
     "{!}
    2.32
    곞
    2.31
    assaytype
    2.30
    POSITIVE LOGITS
     e
    1.88
     an
    1.82
     a
    1.80
     and
    1.78
    on
    1.61
     ed
    1.48
     the
    1.48
    goo
    1.45
    an
    1.44
    oz
    1.42
    Activations Density 0.091%

    No Known Activations