© 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. 153558
    Prev
    Next
    INDEX
    Explanations

    ice-cube tray

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

    allocation, refinance, risk, conditions

    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
     l
    0.58
     Michelangelo
    0.46
     Kinh
    0.45
     Hades
    0.43
     Kurs
    0.42
     Vn
    0.42
     Humans
    0.41
     V
    0.41
     Human
    0.41
     храм
    0.41
    POSITIVE LOGITS
    व्हाण
    0.52
    یز
    0.48
    Fax
    0.46
    槳
    0.46
    গ্
    0.46
     orifices
    0.44
    Vacuum
    0.43
    াব
    0.43
    PropertyGroup
    0.43
    𝗔
    0.43
    Activations Density 0.001%

    No Known Activations