© 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. 59076
    Prev
    Next
    INDEX
    Explanations

    actions, states, or outcomes

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

    commercial use only

    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
     downturn
    0.43
     guarantor
    0.43
     அலங்க
    0.43
     selfie
    0.43
     leggings
    0.43
    徙
    0.43
    Sponsored
    0.42
    裔
    0.41
    馇
    0.40
    ホルダー
    0.40
    POSITIVE LOGITS
    enni
    0.42
    rocessing
    0.41
     일반적으로
    0.41
     Nec
    0.40
    бычно
    0.40
    ີ
    0.38
     Kot
    0.38
     Buf
    0.38
    rocess
    0.38
    onnen
    0.38
    Activations Density 0.001%

    No Known Activations