© 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. 246528
    Prev
    Next
    INDEX
    Explanations

    payment methods and tickets

    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
    REPEAT
    0.55
    стка
    0.52
    트
    0.52
    טו
    0.52
    ტო
    0.52
    竣
    0.51
     Repeat
    0.50
    טה
    0.50
    VING
    0.50
    ト
    0.50
    POSITIVE LOGITS
    abt
    0.46
    َيْ
    0.45
    aba
    0.45
     عنه
    0.44
    infodisc
    0.44
    login
    0.44
     ptr
    0.43
     ត
    0.43
    側
    0.43
    recht
    0.43
    Activations Density 0.000%

    No Known Activations