© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14176
    Prev
    Next
    INDEX
    Explanations

    intermediate results or values

    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
    FORWARD
    2.56
    AnyCPU
    2.35
    ALLY
    2.28
    UIAlert
    2.24
    ANDER
    2.21
    VEY
    2.15
     Judge
    2.14
    𝓬
    2.10
    AB
    2.10
    ם
    2.06
    POSITIVE LOGITS
    া
    2.79
    an
    2.62
    क
    2.58
    anio
    2.50
    anía
    2.47
    دول
    2.43
    arte
    2.29
    حض
    2.26
    고
    2.26
     rownames
    2.24
    Activations Density 0.038%

    No Known Activations