© 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. 149145
    Prev
    Next
    INDEX
    Explanations

    statements to essays

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

    camera features and systems

    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
    hen
    0.47
    舞蹈
    0.45
    (
    0.45
    次的
    0.44
     nga
    0.43
    נ
    0.43
    因為
    0.43
    岡
    0.43
     céré
    0.43
    ikten
    0.43
    POSITIVE LOGITS
     Eqs
    0.54
     substituents
    0.51
     Monographs
    0.49
     Hubert
    0.49
     inhibitors
    0.48
     neighbourhoods
    0.46
     Антон
    0.46
     États
    0.46
     ი
    0.45
     Ulm
    0.45
    Activations Density 0.000%

    No Known Activations