© 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-65K
    7. 48709
    Prev
    Next
    INDEX
    Explanations

    friend / friends

    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_65k_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
    on
    0.78
    <0x80>
    0.63
    Kin
    0.63
    Analysts
    0.60
    Office
    0.56
    於
    0.56
     Organización
    0.55
    τητας
    0.55
     samband
    0.55
     actief
    0.55
    POSITIVE LOGITS
    ین
    0.82
    ک
    0.81
    し
    0.77
     or
    0.70
    л
    0.70
    ك
    0.67
     backpacking
    0.66
    ل
    0.65
     as
    0.64
    یم
    0.64
    Activations Density 0.024%

    No Known Activations