© 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. 145411
    Prev
    Next
    INDEX
    Explanations

    stays, Cruz, trends, highly, stretch, alternative

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

    control, tool, used, critical, different

    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
    小
    0.49
    Screens
    0.49
    Britain
    0.49
    CHANNEL
    0.48
    Boo
    0.48
    ഗ
    0.47
    ⵔ
    0.47
    悅
    0.46
    Kelly
    0.46
    IPLE
    0.46
    POSITIVE LOGITS
     Regist
    0.47
    alid
    0.45
    deserialize
    0.44
     chassis
    0.42
     पीड़ित
    0.42
    utas
    0.42
    fontSize
    0.42
    ிகி
    0.42
    aw
    0.41
    diameter
    0.41
    Activations Density 0.001%

    No Known Activations