© 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. 234593
    Prev
    Next
    INDEX
    Explanations

    can hold, dispute or, houses in, kits, vests, Qatar coincides

    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
    큽
    0.54
    crafted
    0.53
    helpful
    0.52
    improved
    0.50
    大家的
    0.50
    guessed
    0.49
    jangan
    0.49
    वेंट
    0.49
    credit
    0.49
    inspired
    0.49
    POSITIVE LOGITS
    <unused60>
    0.46
     Roque
    0.42
     convoy
    0.41
                    
    0.41
     φ
    0.41
     trang
    0.41
    0.40
     dyst
    0.40
     whilst
    0.40
     NZ
    0.40
    Activations Density 0.000%

    No Known Activations