© 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. 132879
    Prev
    Next
    INDEX
    Explanations

    frida foundry도시 편집

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

    words followed by punctuation or definitions

    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
    ائب
    0.44
    魚
    0.43
    逐步
    0.42
    اردوش
    0.42
    Launcher
    0.41
     isotherm
    0.41
    Grady
    0.41
    وة
    0.40
    ギュ
    0.40
    smallest
    0.40
    POSITIVE LOGITS
     '(
    0.47
     FR
    0.46
     Frid
    0.45
     Foundry
    0.43
     Frida
    0.42
     도시
    0.42
    편집
    0.42
     È
    0.41
     자리
    0.41
    ‍♀
    0.40
    Activations Density 0.000%

    No Known Activations