© 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. 37875
    Prev
    Next
    INDEX
    Explanations

    the building is phones

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

    polar bears are white

    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
    axi
    0.46
     двох
    0.42
    azolid
    0.42
     활
    0.41
    intention
    0.41
     өт
    0.40
     特別
    0.40
    夯
    0.40
    以下的
    0.40
     स्थान
    0.40
    POSITIVE LOGITS
     penalties
    0.46
    মতী
    0.45
     Martyrs
    0.44
     vote
    0.44
     penal
    0.43
     sher
    0.43
     fees
    0.43
     dependents
    0.42
     marks
    0.42
    克斯
    0.42
    Activations Density 0.000%

    No Known Activations