© 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. 159734
    Prev
    Next
    INDEX
    Explanations

    road alignment

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

    written in code or stars

    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
     abiertos
    0.50
    ని
    0.49
    +|\
    0.49
     pubescent
    0.47
     rekao
    0.45
     হইবে
    0.44
    пису
    0.44
     verrez
    0.44
    Rw
    0.43
     baht
    0.43
    POSITIVE LOGITS
    Extreme
    0.49
    Bool
    0.45
    ﮕ
    0.45
    correctAns
    0.45
     extremo
    0.44
     VIA
    0.44
    汽車
    0.44
     തൊ
    0.43
     ആശുപത്രി
    0.42
     जरूरत
    0.42
    Activations Density 0.001%

    No Known Activations