© 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. 25165
    Prev
    Next
    INDEX
    Explanations

    variety of talents

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

    regime actively, reading aloud, often paraphrased, never revealed

    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
    DOWN
    0.46
    WEST
    0.43
     methodName
    0.40
     anharmonic
    0.39
     admixture
    0.38
    ?"
    0.37
    "</
    0.37
    "];
    0.37
     constancy
    0.37
     renormalization
    0.37
    POSITIVE LOGITS
     मॉ
    0.42
     Η
    0.40
     Fokus
    0.40
     Feuilles
    0.39
    ibal
    0.39
    🔘
    0.39
     ईमेल
    0.38
    ający
    0.38
    chester
    0.38
    𝚊
    0.38
    Activations Density 0.000%

    No Known Activations