© 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. 8222
    Prev
    Next
    INDEX
    Explanations

    web or exact information

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

    taking text as input

    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
    asă
    0.42
    ປັນ
    0.40
    ਦ
    0.40
    FloatField
    0.39
    čil
    0.39
    缟
    0.39
    佚
    0.39
    䀼
    0.39
     etanol
    0.38
    iramente
    0.38
    POSITIVE LOGITS
    息
    0.40
    grandchildren
    0.37
    —
    0.36
    localStorage
    0.35
     ense
    0.34
     Lip
    0.34
    lip
    0.34
     घड़ी
    0.34
     gs
    0.34
     Other
    0.33
    Activations Density 0.015%

    No Known Activations