© 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. 132694
    Prev
    Next
    INDEX
    Explanations

    statistics and business terms

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

    can build

    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
     delicacies
    0.46
    MOST
    0.44
    ]
    0.43
    IS
    0.43
    Ralph
    0.43
     visits
    0.43
     embarazada
    0.43
     pasada
    0.42
     faculties
    0.42
    的最
    0.42
    POSITIVE LOGITS
     велосипе
    0.49
     अंधे
    0.47
    تبر
    0.46
     علاوہ
    0.46
    욬
    0.46
     welder
    0.45
     crom
    0.45
    تهم
    0.44
     ለ
    0.44
     втори
    0.44
    Activations Density 0.000%

    No Known Activations