© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56497
    Prev
    Next
    INDEX
    Explanations

    privacy, manipulation, Corp, benchmark

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    0.44
     specializing
    0.43
    ,(
    0.42
     Ballet
    0.40
     Rimini
    0.38
     cóm
    0.38
    ,【
    0.38
    autoprefixer
    0.37
    শুর
    0.37
    ਸ
    0.37
    POSITIVE LOGITS
     lmao
    0.45
    ര്‍ഷ
    0.44
    firebase
    0.43
    ાઇ
    0.42
    ausea
    0.41
    Drinking
    0.41
     schafft
    0.40
     ويك
    0.40
     सुद्धा
    0.40
     ಕಬ್ಬಿಣ
    0.40
    Activations Density 0.023%

    No Known Activations