© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 3879
    Prev
    Next
    INDEX
    Explanations

    code and shell commands

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

    code string and data structures

    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
     adhipp
    0.31
    ឈ្ម
    0.30
    蟎
    0.29
     menjalani
    0.28
     फोटोशूट
    0.28
     कपास
    0.27
    🤱
    0.27
    ទទ
    0.27
    zoomSeekBar
    0.27
    eksiyon
    0.27
    POSITIVE LOGITS
    Unix
    0.28
    int
    0.27
    Factory
    0.25
    c
    0.25
     unix
    0.25
     Unix
    0.24
     temp
    0.24
    Enum
    0.24
    from
    0.24
    String
    0.23
    Activations Density 0.001%

    No Known Activations