© 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. 33192
    Prev
    Next
    INDEX
    Explanations

    aimless search

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

    making things implied infinite

    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
    Their
    0.50
    。\
    0.44
    Furthermore
    0.44
    其
    0.44
    AndUpdate
    0.43
    ときの
    0.43
    時
    0.43
     Their
    0.42
     stoichiometry
    0.42
    孚
    0.42
    POSITIVE LOGITS
    :],
    0.46
     ಪ್ರಕಾರ
    0.45
    scar
    0.45
     azon
    0.44
    alo
    0.44
    ologico
    0.43
    searching
    0.43
     untenable
    0.43
     सॉ
    0.43
     poderia
    0.43
    Activations Density 0.000%

    No Known Activations