© 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. 1995
    Prev
    Next
    INDEX
    Explanations

    name followed by description

    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
     bytecode
    0.31
     pulsation
    0.29
     occlusion
    0.29
     ruin
    0.29
     isomorphisms
    0.28
     ]]
    0.28
    JSPA
    0.28
    <unused79>
    0.28
     embol
    0.28
     "":
    0.27
    POSITIVE LOGITS
    ami
    0.34
    wearing
    0.33
    having
    0.33
    had
    0.32
    aki
    0.32
    rib
    0.31
    using
    0.30
    opting
    0.30
    unlike
    0.30
    ដែលមាន
    0.30
    Activations Density 0.044%

    No Known Activations