© 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. 246062
    Prev
    Next
    INDEX
    Explanations

    cities

    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
     สามารถ
    0.54
     subsets
    0.52
     idealized
    0.52
     predictors
    0.50
     Quadratic
    0.50
    ສາມາດ
    0.50
    ,_
    0.49
     scopes
    0.49
     による
    0.49
     できる
    0.48
    POSITIVE LOGITS
    ент
    0.47
    ene
    0.44
    icky
    0.43
    idos
    0.42
    </tr>
    0.42
    we
    0.42
    ince
    0.41
    고
    0.41
    olved
    0.40
    ása
    0.40
    Activations Density 0.000%

    No Known Activations