© 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. 15111
    Prev
    Next
    INDEX
    Explanations

    causes and limits

    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
    𒆷
    0.59
    𝓗
    0.57
     hMut
    0.54
     भिखारी
    0.50
    acağız
    0.50
     lesquels
    0.50
     рекомен
    0.50
     evanescent
    0.49
    𒂠
    0.49
     АК
    0.49
    POSITIVE LOGITS
    on
    0.63
    -
    0.55
    Marcus
    0.46
     .
    0.46
    Paul
    0.46
    Pren
    0.46
    e
    0.45
    +
    0.45
    however
    0.45
    0
    0.44
    Activations Density 0.001%

    No Known Activations