© 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. 200745
    Prev
    Next
    INDEX
    Explanations

    numbered lists or conditions

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

    introducing specific phrases

    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
     novas
    0.49
     chances
    0.48
     نکال
    0.48
    に使
    0.46
    選
    0.46
    閒
    0.46
    ام
    0.46
    顧問
    0.45
    もら
    0.42
     probabilities
    0.41
    POSITIVE LOGITS
    ки
    0.52
     imediatamente
    0.48
    ți
    0.48
    wohl
    0.47
    ისა
    0.46
     ಎರಡು
    0.46
     --------");
    0.46
    warp
    0.46
    tede
    0.46
    <start_of_turn>
    0.46
    Activations Density 0.000%

    No Known Activations