© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 404
    Prev
    Next
    INDEX
    Explanations

    separators and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    BlockUsed
    0.28
     brû
    0.23
    Roasted
    0.23
    ：「
    0.22
     Encyclop
    0.22
    BufOffset
    0.22
    👳
    0.22
    Khokhlov
    0.21
    <unused51>
    0.21
    ennzeichnet
    0.20
    POSITIVE LOGITS
     the
    0.36
    s
    0.30
    3
    0.30
    4
    0.30
    6
    0.30
    5
    0.29
    2
    0.29
     I
    0.28
    amp
    0.28
    1
    0.27
    Activations Density 2.781%

    No Known Activations