© 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. 243544
    Prev
    Next
    INDEX
    Explanations

    ways to heat your home

    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
    పతి
    0.53
    rimiento
    0.49
     యుద్ధ
    0.49
     करतो
    0.49
    ान्
    0.48
    தனை
    0.48
     ಜಾ
    0.47
     返
    0.46
     పో
    0.46
     Помимо
    0.46
    POSITIVE LOGITS
     digitally
    0.59
     with
    0.55
     as
    0.55
    よく
    0.55
     at
    0.52
     for
    0.51
     Montana
    0.50
     that
    0.49
     mysteriously
    0.49
    の
    0.49
    Activations Density 0.000%

    No Known Activations