© 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. 150207
    Prev
    Next
    INDEX
    Explanations

    pool pump submersible

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

    risk, assessment, camera

    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
    чи
    0.56
    וב
    0.51
    𝘆
    0.51
    𝗼
    0.50
    чі
    0.50
    𝒐
    0.50
     convirt
    0.50
    𝙤
    0.50
    𝚛
    0.49
    ম্যান
    0.49
    POSITIVE LOGITS
    lipid
    0.52
     lipid
    0.43
     invertebrate
    0.42
    0.42
     immutable
    0.42
     (
    0.41
     when
    0.41
     immune
    0.40
     gal
    0.40
    drawing
    0.40
    Activations Density 0.001%

    No Known Activations