© 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. 68770
    Prev
    Next
    INDEX
    Explanations

    this followed by nouns

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

    temperature, pool, specific descriptors

    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
     outfitted
    0.49
     aboard
    0.48
     MSNBC
    0.45
     ♦
    0.44
    reli
    0.43
    halter
    0.43
     legitimately
    0.43
    behör
    0.43
     느낌
    0.42
    hitva
    0.41
    POSITIVE LOGITS
     odc
    0.52
    Sections
    0.49
    COND
    0.46
    า
    0.45
    MED
    0.45
    ή
    0.45
    მი
    0.45
    Vectors
    0.45
     vra
    0.43
    ้วน
    0.43
    Activations Density 0.000%

    No Known Activations