© 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. 138529
    Prev
    Next
    INDEX
    Explanations

    college essay and descriptive writing

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

    travel and specific evaluations

    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
    ظيم
    0.55
     ينت
    0.50
    পড়
    0.50
    reed
    0.49
    ungs
    0.49
    ตรา
    0.49
    踺
    0.48
     бюд
    0.48
     Зем
    0.48
    鸷
    0.47
    POSITIVE LOGITS
     Tempest
    0.49
     falsehood
    0.48
     tempest
    0.46
     If
    0.44
     attraverso
    0.44
     recollection
    0.44
    ↵
    0.43
     prosthesis
    0.43
    moy
    0.42
     syntax
    0.42
    Activations Density 0.000%

    No Known Activations