© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1701
    Prev
    Next
    INDEX
    Explanations

    Japanese, British, Russian entities

    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
     In
    1.57
    <0xF3>
    1.55
    This
    1.51
    In
    1.50
     This
    1.45
    The
    1.44
     from
    1.44
     Und
    1.42
    '
    1.40
     With
    1.39
    POSITIVE LOGITS
     kehnd
    2.39
    <unused1187>
    2.20
    octrl
    2.16
    baseHP
    2.10
    apetva
    2.10
    <unused1208>
    2.09
    besiege
    2.09
    armafit
    2.08
    bibfield
    2.08
    <unused1153>
    2.07
    Activations Density 0.145%

    No Known Activations