© 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. 124262
    Prev
    Next
    INDEX
    Explanations

    primary focuses, social media, rings, fan

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

    hidden room reading

    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
    spers
    0.45
    ས་
    0.41
    ikations
    0.41
    सेने
    0.41
    y
    0.40
    iyê
    0.40
    neys
    0.40
    мите
    0.40
    شن
    0.39
     situés
    0.39
    POSITIVE LOGITS
     ৯০
    0.48
    р
    0.47
    aktif
    0.46
     .;
    0.46
     Arz
    0.46
     そんな
    0.45
     核
    0.45
    ۹
    0.45
     ভ্রম
    0.44
     सोलर
    0.44
    Activations Density 0.000%

    No Known Activations