© 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. 97671
    Prev
    Next
    INDEX
    Explanations

    is specialized, is a professional

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

    sometimes providers

    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
     HSPB
    0.48
    对话
    0.47
    Dialog
    0.47
    Dialogue
    0.46
     hia
    0.46
     имму
    0.43
    Section
    0.43
    ;&
    0.43
    lx
    0.42
    inositol
    0.42
    POSITIVE LOGITS
     sometimes
    0.53
     soms
    0.53
     manchmal
    0.49
     használ
    0.48
     podido
    0.47
     promos
    0.47
     gebruiken
    0.46
     gebruikt
    0.46
     trabajado
    0.45
     used
    0.45
    Activations Density 0.002%

    No Known Activations