© 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. 12984
    Prev
    Next
    INDEX
    Explanations

    years with citations

    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
    0
    0.55
    ?
    0.52
    .
    0.49
    </h3>
    0.46
    _
    0.46
    </h1>
    0.44
    %
    0.44
    К
    0.44
    </h2>
    0.43
    ln
    0.42
    POSITIVE LOGITS
     ప్రయత్
    0.44
    鴳
    0.41
    秾
    0.40
    लाइड
    0.40
     máscara
    0.40
    ༸
    0.40
     frizz
    0.39
     dihydro
    0.39
    鹖
    0.38
    ម្លៃ
    0.38
    Activations Density 0.010%

    No Known Activations