© 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. 220344
    Prev
    Next
    INDEX
    Explanations

    copper orecalling artmay keep

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

    configuration, maintenance, or specific actions

    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
     discontinuities
    0.49
    ր
    0.48
    ירת
    0.44
    ल्ड
    0.44
     diodes
    0.44
     composers
    0.44
     parts
    0.43
     discontinuity
    0.43
     bumps
    0.43
    reached
    0.42
    POSITIVE LOGITS
    }
    0.59
     Кай
    0.59
    їн
    0.51
     ала
    0.47
    可以让
    0.47
     Enabling
    0.47
     अह
    0.46
     علي
    0.45
     عنده
    0.45
    ية
    0.45
    Activations Density 0.001%

    No Known Activations