© 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. 32996
    Prev
    Next
    INDEX
    Explanations

    biggest India character store

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

    exam, geometry, shortcut, direct consequence

    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
     onion
    0.46
     inspectors
    0.44
     earliest
    0.43
     commands
    0.43
    ابقات
    0.42
    賜
    0.42
     commanded
    0.41
    }<\
    0.40
     perintah
    0.40
    اه
    0.39
    POSITIVE LOGITS
    ische
    0.54
    absorption
    0.52
    ito
    0.51
    liche
    0.51
    şti
    0.50
    very
    0.50
    ến
    0.49
    iseen
    0.49
    much
    0.48
     अरे
    0.48
    Activations Density 0.000%

    No Known Activations