© 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. 157241
    Prev
    Next
    INDEX
    Explanations

    nicotine levels, know how, explicit specification

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

    conditions and management

    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
     cheeks
    0.49
    ῆ
    0.47
     করিয়াছিল
    0.47
     femoral
    0.47
    ！」
    0.45
     amyg
    0.44
     committing
    0.44
     womans
    0.44
    iest
    0.44
     amma
    0.44
    POSITIVE LOGITS
    グルメ
    0.42
    DESCRIPTION
    0.39
     weiter
    0.38
    р
    0.38
     revamped
    0.37
    传送
    0.37
    强势
    0.37
    Quantitative
    0.37
     Architectural
    0.36
    Owner
    0.36
    Activations Density 0.001%

    No Known Activations