© 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. 202523
    Prev
    Next
    INDEX
    Explanations

    car washing

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

    good and evil, transition time

    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
     Clarendon
    0.54
    S
    0.53
     St
    0.51
    "
    0.51
     Cap
    0.50
    6
    0.50
     Ces
    0.49
     Cesar
    0.49
    7
    0.49
     Comedy
    0.48
    POSITIVE LOGITS
    ointments
    0.56
    esthetic
    0.52
    atron
    0.51
    igrants
    0.51
    agro
    0.50
    etzten
    0.50
    eep
    0.49
    िश्वत
    0.49
    rients
    0.49
    obuf
    0.49
    Activations Density 0.000%

    No Known Activations