© 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. 172589
    Prev
    Next
    INDEX
    Explanations

    interest in offers or information

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

    filters and budget

    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
     Fungsi
    0.55
    łącznie
    0.50
    on
    0.50
    Remote
    0.49
    Adress
    0.49
    યર
    0.48
     \|
    0.47
    密码
    0.46
    error
    0.46
     Beding
    0.46
    POSITIVE LOGITS
     mortars
    0.47
    يكل
    0.45
     graduates
    0.44
    <h2>
    0.44
     grandes
    0.44
     surpluses
    0.43
    UMPS
    0.43
     ಪ್ರತಿ
    0.43
     মর্টার
    0.42
     NASCAR
    0.42
    Activations Density 0.000%

    No Known Activations