© 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. 226191
    Prev
    Next
    INDEX
    Explanations

    third party context

    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
     expir
    0.54
     extol
    0.53
     Laus
    0.52
     tentativa
    0.52
     加
    0.51
     cio
    0.51
     concili
    0.51
     何
    0.50
    عيه
    0.49
     Braga
    0.49
    POSITIVE LOGITS
    țe
    0.50
    ље
    0.49
    ٹنے
    0.48
    ਹ
    0.47
    ٹے
    0.47
    া
    0.47
    ੱ
    0.46
    ڑے
    0.46
    ipped
    0.46
    efficient
    0.45
    Activations Density 0.000%

    No Known Activations