© 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. 84125
    Prev
    Next
    INDEX
    Explanations

    thank you for actions

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

    manage complex functions

    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
     slowed
    0.43
    ྱི་
    0.42
    picks
    0.42
    ՛
    0.42
    phonic
    0.40
     էր
    0.40
    givers
    0.40
     αν
    0.39
     β
    0.39
     pissed
    0.39
    POSITIVE LOGITS
    denum
    0.45
     ())
    0.44
    며
    0.44
     .)
    0.42
    侢
    0.42
     *)
    0.40
     Waren
    0.40
    னோ
    0.40
     월
    0.40
    uchos
    0.39
    Activations Density 0.001%

    No Known Activations