© 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. 128518
    Prev
    Next
    INDEX
    Explanations

    department mechanical

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

    installing programs

    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
    пература
    0.44
     sucked
    0.43
    貸
    0.43
     Hora
    0.42
    npj
    0.42
    讫
    0.41
     decap
    0.40
     পুত্র
    0.40
     долго
    0.40
     изменение
    0.40
    POSITIVE LOGITS
    ⌵
    0.47
    isPreview
    0.46
     Biotechnology
    0.45
     vaak
    0.44
    য়র
    0.43
     oasis
    0.42
    ొప్పి
    0.41
     hva
    0.40
    ází
    0.40
     pres
    0.40
    Activations Density 0.001%

    No Known Activations