© 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. 5097
    Prev
    Next
    INDEX
    Explanations

    several other some few

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

    few, several, some

    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
     घेऊ
    0.47
     करू
    0.40
    㨁
    0.40
    koord
    0.38
    direita
    0.38
    куса
    0.37
    valuate
    0.37
     അവളെ
    0.37
    .[[
    0.36
    눠
    0.36
    POSITIVE LOGITS
     Several
    0.99
    Several
    0.86
     several
    0.79
     Various
    0.74
     Few
    0.72
    several
    0.71
     various
    0.71
    Various
    0.70
     Some
    0.69
    Few
    0.67
    Activations Density 0.126%

    No Known Activations