© 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. 186353
    Prev
    Next
    INDEX
    Explanations

    believeth is condemned

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

    increases, selling, training, sharpness, refined

    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
     سور
    0.51
     caj
    0.47
    ezza
    0.47
     צ
    0.46
    翼
    0.45
     cysteine
    0.43
     కాని
    0.43
    ฉ
    0.43
     هش
    0.42
    智
    0.42
    POSITIVE LOGITS
     či
    0.46
    𝗬
    0.46
    ilik
    0.44
     ataupun
    0.44
    рті
    0.44
     iaitu
    0.43
    ,"+
    0.43
     bunların
    0.43
    THERE
    0.42
    পূর্বে
    0.42
    Activations Density 0.000%

    No Known Activations