© 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. 138510
    Prev
    Next
    INDEX
    Explanations

    look for [name] placeholder page

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

    offering temporary, low to, slower to

    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
    than
    0.52
    ва
    0.49
    Australia
    0.49
    grabbing
    0.49
    让
    0.49
    ATTRIBUTE
    0.48
    ي
    0.48
    compared
    0.47
    יש
    0.46
    creates
    0.46
    POSITIVE LOGITS
     chast
    0.46
     jubil
    0.44
    ectic
    0.44
    टो
    0.43
     medici
    0.43
     Tope
    0.42
    蟠
    0.42
     cusp
    0.42
     mida
    0.41
     نتیجہ
    0.41
    Activations Density 0.001%

    No Known Activations