© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7406
    Prev
    Next
    INDEX
    Explanations

    home and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    home contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doma
    0.47
     дома
    0.42
    Voc
    0.40
     집에
    0.40
    حية
    0.39
    的精神
    0.37
    $/../../
    0.36
     thuis
    0.36
    <0x0D>
    0.36
    ালে
    0.36
    POSITIVE LOGITS
    owners
    0.91
    ostatic
    0.81
    🏡
    0.80
    comings
    0.79
    opathic
    0.76
    ownership
    0.75
    brew
    0.74
    🏠
    0.74
     sweet
    0.71
    opath
    0.71
    Activations Density 0.145%

    No Known Activations