© 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. 27673
    Prev
    Next
    INDEX
    Explanations

    service and reviews

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

    list items and parameters

    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
     sequenced
    0.42
    一种
    0.41
     sustainably
    0.41
    하던
    0.40
     zz
    0.39
     nonché
    0.39
    for
    0.38
     (**
    0.38
     intravascular
    0.38
     (`
    0.38
    POSITIVE LOGITS
    Jogador
    0.46
    jogador
    0.45
     defaultdict
    0.43
     jogador
    0.41
     vantagens
    0.40
    ટ્સ
    0.38
    チャンネル
    0.38
     преимущества
    0.38
    igenschaften
    0.38
    規格
    0.37
    Activations Density 0.005%

    No Known Activations