© 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. 134134
    Prev
    Next
    INDEX
    Explanations

    appointments, membership, or roles

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

    members, supplier, shared

    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
     ventanas
    0.46
    ਯ
    0.46
    тою
    0.43
    ख़
    0.43
     поя
    0.42
     flows
    0.42
     fordul
    0.42
    亞洲
    0.41
    烏
    0.41
    出現
    0.41
    POSITIVE LOGITS
    supplier
    0.52
    member
    0.50
    kipun
    0.46
    an
    0.45
    chosen
    0.45
    tarif
    0.44
    yearly
    0.44
    andidate
    0.44
    studentid
    0.44
    ister
    0.43
    Activations Density 0.000%

    No Known Activations