© 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-262K
    7. 30240
    Prev
    Next
    INDEX
    Explanations

    ownership and release

    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_262k_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
    ri
    0.43
    ake
    0.43
     हवाले
    0.42
    áno
    0.42
    lijah
    0.41
     vengan
    0.41
    oucault
    0.41
    😈
    0.41
    <0x84>
    0.41
     Thiago
    0.41
    POSITIVE LOGITS
     shortlisted
    0.43
     centres
    0.43
     public
    0.42
     Bets
    0.42
     squares
    0.41
     Oils
    0.41
     svim
    0.41
     nimble
    0.40
     Oat
    0.40
     Describes
    0.40
    Activations Density 0.004%

    No Known Activations