© 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. 199536
    Prev
    Next
    INDEX
    Explanations

    following his

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

    academic purposes

    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
    ᴸ
    0.47
    _.
    0.46
     Subsection
    0.44
    ple
    0.43
    昨日
    0.43
    ᵛ
    0.42
    みる
    0.42
    ⇅
    0.42
    葳
    0.42
    Cline
    0.41
    POSITIVE LOGITS
     برش
    0.47
    ей
    0.46
     influência
    0.46
     заня
    0.46
     bootstra
    0.46
    он
    0.46
    حظ
    0.44
    ет
    0.44
     enorm
    0.44
     bootstrap
    0.43
    Activations Density 0.000%

    No Known Activations