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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 9035
    Prev
    Next
    INDEX
    Explanations

    past action verbs

    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_17_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
    -\
    2.17
    一定的
    2.08
    ings
    1.96
    {\|
    1.94
    েল
    1.89
    ^{-}
    1.86
     След
    1.82
    ographic
    1.79
    িং
    1.76
     або
    1.74
    POSITIVE LOGITS
     volna
    4.30
     anteriormente
    2.75
    también
    2.58
     autrefois
    2.58
     бы
    2.57
    s
    2.42
    śmy
    2.26
     auparavant
    2.20
    𝐧
    2.15
    reté
    2.11
    Activations Density 0.295%

    No Known Activations