© 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. 251626
    Prev
    Next
    INDEX
    Explanations

    are quite, are definitely, are rather

    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
    ategory
    0.54
    िया
    0.53
    แก้ไข
    0.52
    ॅन
    0.49
     sensibilité
    0.48
     ریا
    0.48
    힝
    0.48
    γκ
    0.47
     რუს
    0.47
    änd
    0.46
    POSITIVE LOGITS
    s
    0.50
     deceived
    0.47
    Soda
    0.46
    褚
    0.45
     exclaimed
    0.45
    !">
    0.45
    tio
    0.44
     ال
    0.44
    ㄅ
    0.44
     PUBL
    0.44
    Activations Density 0.001%

    No Known Activations