© 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. 7149
    Prev
    Next
    INDEX
    Explanations

    interrupted. denying tax. table while. which Akademie. innovation plus. comparisons among. SCHAEFER. versions with

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

    saving as .py file

    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
    ండ
    0.42
    ,]
    0.40
    aacute
    0.40
    多数
    0.40
    astanza
    0.38
    ,!
    0.38
    ួល
    0.37
     <!
    0.37
    ,.
    0.37
    ,--
    0.37
    POSITIVE LOGITS
     diffe
    0.45
     viii
    0.44
     Những
    0.44
     Usa
    0.43
     cy
    0.43
     cory
    0.43
    被害
    0.41
    ऱ्या
    0.41
     î
    0.39
     victim
    0.39
    Activations Density 0.008%

    No Known Activations