© 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. 60408
    Prev
    Next
    INDEX
    Explanations

    numbers and words

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

    diversity and variety

    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
     fiabilité
    0.55
     सुप्रभात
    0.46
     برج
    0.45
     สามารถ
    0.44
     Qf
    0.44
     Rafa
    0.44
     ラウンド
    0.43
     戦
    0.43
     ن
    0.42
    嵬
    0.42
    POSITIVE LOGITS
    ERICK
    0.48
    BEGIN
    0.44
     hasilnya
    0.43
    ARRAY
    0.41
    xlabel
    0.40
    their
    0.40
    ActionListener
    0.40
    HCl
    0.40
    acrylic
    0.40
     zatim
    0.39
    Activations Density 0.000%

    No Known Activations