© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126263
    Prev
    Next
    INDEX
    Explanations

    new, end, belongs, appearance

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

    Rammstein and chatbots

    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_31_width_262k_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
    ות
    0.56
    ോ
    0.53
    摳
    0.52
     RAC
    0.48
    וני
    0.48
    ку
    0.45
    chließlich
    0.45
    ית
    0.45
     RMA
    0.45
     মোতাবেক
    0.45
    POSITIVE LOGITS
     правила
    0.47
     diagnosis
    0.46
    postgresql
    0.43
     Diagnosis
    0.43
     үй
    0.42
     т
    0.42
     φύ
    0.42
     rules
    0.42
    岡山
    0.41
     сердца
    0.41
    Activations Density 0.001%

    No Known Activations