© 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. 124548
    Prev
    Next
    INDEX
    Explanations

    common, same, ideas, reunion, salt, surveys

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

    subject or event headings

    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
     Students
    0.44
    াপনের
    0.43
     રહે
    0.43
    ্
    0.43
     Actors
    0.42
    ानीय
    0.41
     Nh
    0.41
     ഡ
    0.40
    或是
    0.40
     DISC
    0.40
    POSITIVE LOGITS
    texte
    0.52
    pointe
    0.52
    stvo
    0.51
    like
    0.47
    gluten
    0.47
    nut
    0.47
    abbas
    0.46
    vos
    0.45
    vog
    0.45
    ienten
    0.45
    Activations Density 0.000%

    No Known Activations