© 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. 66280
    Prev
    Next
    INDEX
    Explanations

    numbers and subsequent words

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

    technical descriptions and explanations

    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
     تھی۔
    0.42
    ippers
    0.41
     Gesam
    0.41
     Immortal
    0.39
     Foods
    0.39
     Beverly
    0.39
    苳
    0.38
     Millions
    0.38
     siglos
    0.38
     XXII
    0.38
    POSITIVE LOGITS
     facilit
    0.46
    াড়ি
    0.45
     suna
    0.45
    ೇಳ
    0.45
    ড়া
    0.44
     제도
    0.43
     добавля
    0.43
    ç
    0.42
    হাম
    0.41
    ではなく
    0.41
    Activations Density 0.001%

    No Known Activations