© 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. 145849
    Prev
    Next
    INDEX
    Explanations

    book, writing, or specific phrases

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

    Vicuna, managed, roofing, for

    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
    ﺓ
    0.55
    ﻳ
    0.51
     الخط
    0.50
    geber
    0.47
    gever
    0.47
     suited
    0.46
    །
    0.45
    شاه
    0.45
    Ყ
    0.45
    Sender
    0.45
    POSITIVE LOGITS
     như
    0.49
     ஒன்றாகும்
    0.48
     Hern
    0.47
    俟
    0.46
     väga
    0.46
     Cities
    0.45
    GDP
    0.44
     প্রাসাদ
    0.43
    ){\
    0.42
     Subsec
    0.42
    Activations Density 0.000%

    No Known Activations