© 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. 99230
    Prev
    Next
    INDEX
    Explanations

    whether, if, that

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

    despite the chill

    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
    导航
    0.46
     ಯೋಜ
    0.45
    ጥ
    0.45
    wig
    0.44
    USS
    0.44
     její
    0.44
     corpse
    0.43
    photon
    0.42
     mistress
    0.42
     її
    0.42
    POSITIVE LOGITS
     Aper
    0.46
    岀
    0.45
     Variations
    0.45
     Chur
    0.44
     Appet
    0.43
     Prit
    0.43
     Development
    0.43
     Advancement
    0.42
    唦
    0.42
     SEQ
    0.42
    Activations Density 0.000%

    No Known Activations