© 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. 42782
    Prev
    Next
    INDEX
    Explanations

    website, organic, tea, industry

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

    due to, streamlined approach, Python, Undertale

    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
    ut
    0.59
    will
    0.52
     will
    0.51
    ிருக்கும்
    0.51
    U
    0.51
    ui
    0.50
    IGHT
    0.48
    ven
    0.47
     подс
    0.47
    ves
    0.46
    POSITIVE LOGITS
     concatenation
    0.49
    来て
    0.48
    ದಗ
    0.46
    ބ
    0.46
    دیا
    0.46
     duomen
    0.46
     excesses
    0.45
     üks
    0.45
     istnie
    0.44
    دوس
    0.44
    Activations Density 0.000%

    No Known Activations