© 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. 16-GEMMASCOPE-2-RES-262K
    7. 109803
    Prev
    Next
    INDEX
    Explanations

    sedative, sedation, or ma

    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_16_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
    ش
    0.67
    ம்
    0.66
    ം
    0.59
    트를
    0.55
    ي
    0.52
     chambre
    0.52
     सी
    0.50
    어를
    0.49
     penetrated
    0.49
     software
    0.49
    POSITIVE LOGITS
    ll
    0.63
    la
    0.58
    lah
    0.57
    d
    0.54
    lus
    0.54
    label
    0.53
    Стро
    0.52
    lam
    0.50
    dk
    0.50
    llan
    0.49
    Activations Density 0.000%

    No Known Activations