© 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. 228258
    Prev
    Next
    INDEX
    Explanations

    pronunciation and specific terms

    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
    "
    0.61
    *
    0.56
    *,
    0.49
     ntawm
    0.49
    "+
    0.49
    #
    0.48
    »
    0.44
     από
    0.44
    "$
    0.43
    ‘
    0.43
    POSITIVE LOGITS
     shallower
    0.47
     Krieg
    0.43
    リビング
    0.43
    討
    0.42
     shallow
    0.42
    पोरेशन
    0.42
    ইহ
    0.41
     यात
    0.41
     தேர்தலில்
    0.41
    hooting
    0.41
    Activations Density 0.000%

    No Known Activations