© 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. 7061
    Prev
    Next
    INDEX
    Explanations

    doing or being followed by outcomes

    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
    ی
    0.91
    它
    0.88
    ال
    0.80
    it
    0.77
    사
    0.77
    ের
    0.76
    র
    0.74
     it
    0.73
    나
    0.68
    на
    0.67
    POSITIVE LOGITS
    -
    0.86
    ton
    0.72
    ting
    0.63
    <0x80>
    0.62
    <0xA3>
    0.61
     oneself
    0.58
    ly
    0.56
    tais
    0.56
    lessness
    0.55
    ta
    0.54
    Activations Density 0.467%

    No Known Activations