© 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. 251729
    Prev
    Next
    INDEX
    Explanations

    helping Timber

    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
     өл
    0.49
    =""
    0.46
    ТИ
    0.46
    आ
    0.45
    ТО
    0.45
     TOTAL
    0.44
    自治区
    0.44
    க
    0.44
     धर
    0.44
    ב
    0.44
    POSITIVE LOGITS
    WaitingTime
    0.46
    KeyCode
    0.45
     হিন্দি
    0.45
    ippi
    0.43
    iggle
    0.43
    ριο
    0.43
    ppsala
    0.43
     minimalistic
    0.42
     rye
    0.42
    ንን
    0.42
    Activations Density 0.000%

    No Known Activations