© 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. 139239
    Prev
    Next
    INDEX
    Explanations

    downstream demand or Belarus Premier

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

    BIOS/UEFI and spread

    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
    礦
    0.43
    -(\
    0.41
    മായ
    0.41
    東北
    0.40
    簡單
    0.40
    若い
    0.39
    <unused2000>
    0.39
     avanzando
    0.39
     bookkeeping
    0.39
    錒
    0.39
    POSITIVE LOGITS
    ﺵ
    0.46
    Tik
    0.45
    뜰
    0.45
    es
    0.44
    ữ
    0.44
     wers
    0.43
    कद
    0.43
    kts
    0.43
    वटी
    0.43
    ذیر
    0.42
    Activations Density 0.000%

    No Known Activations