© 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. 173248
    Prev
    Next
    INDEX
    Explanations

    principal's success

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

    coupons, limits, GPU, narrative, services

    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
    tR
    0.54
    t
    0.54
     ৰ
    0.50
    һ
    0.50
     움
    0.48
    iranje
    0.46
     fhould
    0.46
     sicherlich
    0.46
     conferences
    0.46
     Ј
    0.46
    POSITIVE LOGITS
    FANG
    0.46
    ந்து
    0.44
    Env
    0.44
    ندی
    0.42
    Operand
    0.42
    }^{+}$.
    0.42
    ributive
    0.42
    류
    0.42
    Pd
    0.42
    چی
    0.41
    Activations Density 0.000%

    No Known Activations