© 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. 202180
    Prev
    Next
    INDEX
    Explanations

    gold filled, inlay, laminated, pants

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

    long SMA, training data, continued strong

    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
     Meals
    0.48
     hacking
    0.46
     moderately
    0.43
    }\|\
    0.42
     concentrate
    0.42
     Frag
    0.42
     Poverty
    0.42
    opoulos
    0.41
     Free
    0.41
     Hack
    0.41
    POSITIVE LOGITS
    κέ
    0.60
    レシ
    0.55
    ５
    0.50
    codewords
    0.50
    кож
    0.49
    скім
    0.48
    
    0.48
     کړ
    0.48
    ੰਜ
    0.48
     medži
    0.48
    Activations Density 0.001%

    No Known Activations