© 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. 252311
    Prev
    Next
    INDEX
    Explanations

    mechanism, ideas, inspiration

    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
     IPO
    0.47
     marrow
    0.46
     myeloid
    0.46
     astrophys
    0.45
     LAND
    0.45
     astrophysical
    0.44
     chewy
    0.44
    酶
    0.44
     EMU
    0.44
     mitigated
    0.43
    POSITIVE LOGITS
    currentColor
    0.46
     답
    0.45
    suitable
    0.45
    üt
    0.45
     toată
    0.44
    klad
    0.43
     послед
    0.42
     써
    0.42
    Classification
    0.42
    ěn
    0.42
    Activations Density 0.000%

    No Known Activations