© 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. 31261
    Prev
    Next
    INDEX
    Explanations

    implementations and technical details

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

    well, well, well / unlock / ensure

    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
    וד
    0.49
     ಸೇವ
    0.47
     Și
    0.45
    痍
    0.45
     Skyscrapers
    0.45
    メンズ
    0.44
    決して
    0.44
    をもって
    0.44
    সাম
    0.43
     '';
    0.43
    POSITIVE LOGITS
    FormControl
    0.47
    cích
    0.47
    implement
    0.46
    ниця
    0.46
     implements
    0.44
    Implement
    0.43
    orie
    0.43
    t
    0.43
     apr
    0.42
     branche
    0.42
    Activations Density 0.000%

    No Known Activations