© 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. 39856
    Prev
    Next
    INDEX
    Explanations

    building and attraction

    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
     momenti
    0.46
     Estadística
    0.45
    QTTR
    0.45
     വ്യത്യസ്ത
    0.44
    ').
    0.44
    '}).
    0.44
     بولی
    0.43
    ناها
    0.43
     учителя
    0.43
    Ố
    0.43
    POSITIVE LOGITS
     tackles
    0.48
     and
    0.46
     prevent
    0.45
     dwarves
    0.44
    <0x82>
    0.44
     There
    0.43
     grafts
    0.42
     bungalows
    0.42
     geographies
    0.42
     opinions
    0.41
    Activations Density 0.001%

    No Known Activations