© 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. 134172
    Prev
    Next
    INDEX
    Explanations

    Los Angeles

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

    describing characteristics or conditions

    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
     calcS
    0.47
     warships
    0.46
    सैन
    0.45
     щоб
    0.44
    羋
    0.43
     Процитовано
    0.43
    谒
    0.43
    拿着
    0.43
     чтобы
    0.42
    冚
    0.42
    POSITIVE LOGITS
    dt
    0.55
    los
    0.52
    نى
    0.50
    Person
    0.48
    addr
    0.47
    better
    0.47
    mejor
    0.47
    address
    0.47
    paren
    0.46
     bättre
    0.46
    Activations Density 0.000%

    No Known Activations