© 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. 974
    Prev
    Next
    INDEX
    Explanations

    prompt generator

    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
    ੲ
    0.50
    ونکہ
    0.50
    ങ്കിലും
    0.48
    OLYBDENUM
    0.47
    ᒻ
    0.46
     préparations
    0.46
    onnage
    0.46
    unehmen
    0.46
     Wochschr
    0.44
    "+"|".
    0.44
    POSITIVE LOGITS
     No
    0.50
     here
    0.47
     ফিরে
    0.46
     Catalina
    0.45
     Galer
    0.45
    მა
    0.44
     Feels
    0.44
     Nicht
    0.44
     Bloody
    0.44
     הט
    0.43
    Activations Density 0.002%

    No Known Activations