© 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. 2071
    Prev
    Next
    INDEX
    Explanations

    copyright, rights, exporters, manufacturers

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

    1-800-656-HOPE

    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
    R
    0.84
    Robert
    0.75
    Richard
    0.74
     Robert
    0.73
     Richard
    0.72
     Rabu
    0.72
     Rumah
    0.71
     ڕ
    0.67
     merupakan
    0.66
     rencana
    0.66
    POSITIVE LOGITS
     culp
    0.43
     ৪৮
    0.42
    ᴄ
    0.42
    ❖
    0.41
     स्क्रीनिंग
    0.41
    fc
    0.41
     část
    0.41
     chiefly
    0.40
     části
    0.40
     статье
    0.39
    Activations Density 0.338%

    No Known Activations