© 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. 9-GEMMASCOPE-2-RES-16K
    7. 36
    Prev
    Next
    INDEX
    Explanations

    letters and numbers

    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_9_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
    at
    2.32
    in
    2.27
    on
    2.24
    y
    2.10
    an
    2.08
    r
    2.07
    u
    2.02
    as
    1.94
    am
    1.91
    al
    1.74
    POSITIVE LOGITS
    Á
    1.22
    İ
    1.16
     partir
    1.10
     través
    1.07
    Ч
    1.03
    Í
    1.01
    Ι
    1.00
    Ö
    0.98
     Bereits
    0.98
    Ü
    0.98
    Activations Density 1.411%

    No Known Activations