© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 55236
    Prev
    Next
    INDEX
    Explanations

    generally follows specific words

    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
    łę
    0.50
    流程
    0.48
    ar
    0.47
    л
    0.45
    etheus
    0.45
    ленный
    0.44
    лло
    0.43
    武
    0.43
    ován
    0.42
    ństwo
    0.41
    POSITIVE LOGITS
     Detox
    0.45
     verbessert
    0.44
     migliorare
    0.43
    นี่
    0.42
    ക്കാർ
    0.42
     =
    0.42
     summertime
    0.42
     Verbesser
    0.41
    ὑ
    0.41
    Aqui
    0.41
    Activations Density 0.014%

    No Known Activations