© 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. 204958
    Prev
    Next
    INDEX
    Explanations

    safety, accuracy, suitability

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

    types, placeholder, key, underground

    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
     referrals
    0.48
    referrer
    0.47
    柜
    0.47
     Referral
    0.44
    标题
    0.43
     volunteered
    0.43
    associazione
    0.43
     प्रतियोग
    0.42
     referral
    0.41
    替
    0.40
    POSITIVE LOGITS
    య
    0.47
     gotovo
    0.47
     בצ
    0.46
     Invisalign
    0.46
    KIS
    0.45
    覺
    0.45
    ACITY
    0.45
     মিড
    0.44
     ચમ
    0.44
    ју
    0.44
    Activations Density 0.000%

    No Known Activations