Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 50
    Prev
    Next
    INDEX
    Explanations

    possessive or plural `s`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DBGPRINT
    1.09
    LuaPush
    1.07
    ੪
    1.05
    CriteriaUtils
    1.01
     bitOp
    0.99
    मियल
    0.98
    嵃
    0.98
     odnosno
    0.98
     worldRank
    0.98
     zemlje
    0.97
    POSITIVE LOGITS
    ,
    1.48
    .
    1.12
     a
    1.10
     in
    1.07
     the
    1.06
     an
    1.03
     that
    1.03
     at
    1.01
     (
    0.96
     to
    0.93
    Activations Density 0.284%

    No Known Activations