© 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. 60716
    Prev
    Next
    INDEX
    Explanations

    market, island, shift, look

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

    mountain, looking, share

    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
     sink
    0.47
    Processing
    0.47
    Ｄ
    0.45
    Drone
    0.45
     framebuffer
    0.44
    it
    0.44
     drone
    0.44
    сног
    0.44
    視
    0.44
    Config
    0.44
    POSITIVE LOGITS
     Affidavit
    0.44
     সত্যা
    0.43
     Equations
    0.42
     পৌঁ
    0.42
     मातरम
    0.42
     फतेह
    0.41
     Coefficients
    0.41
     อาท
    0.41
    ୂ
    0.41
    कार्ट
    0.40
    Activations Density 0.001%

    No Known Activations