© 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. 251735
    Prev
    Next
    INDEX
    Explanations

    condition, rule, or warranty

    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
     trucking
    0.55
    ית
    0.51
     pathos
    0.51
     एसएस
    0.50
    OTROS
    0.50
    𒅴
    0.50
     microbiology
    0.49
    占い
    0.49
     homeostasis
    0.48
     whenever
    0.48
    POSITIVE LOGITS
    mag
    0.54
    and
    0.49
    zen
    0.49
     A
    0.48
    zeta
    0.48
    ху
    0.46
    ạnh
    0.46
    5
    0.45
    ဖြေ
    0.44
    alpha
    0.44
    Activations Density 0.001%

    No Known Activations