© 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. 227741
    Prev
    Next
    INDEX
    Explanations

    police encounter, claims act

    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
     се
    0.50
     ми
    0.47
    stelle
    0.47
    buje
    0.46
     ее
    0.46
     ра
    0.45
    iligung
    0.45
    著
    0.45
     меди
    0.45
     любви
    0.45
    POSITIVE LOGITS
    ępnie
    0.47
    ophages
    0.46
     racetr
    0.45
    Azer
    0.44
    ᱚ
    0.44
    ocytes
    0.43
    AX
    0.43
    आख
    0.43
     neutrophils
    0.43
    Mobs
    0.42
    Activations Density 0.000%

    No Known Activations