© 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. 158733
    Prev
    Next
    INDEX
    Explanations

    business partners and disclosures

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

    Pending

    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
     každý
    0.46
    ழ்க
    0.45
    埥
    0.44
    ध्याय
    0.44
     دائما
    0.43
     সবসময়
    0.43
     Shipment
    0.42
    㑅
    0.41
    Bound
    0.41
    yste
    0.41
    POSITIVE LOGITS
     வினை
    0.45
     ಹಾಗೂ
    0.45
    ⠛
    0.44
     miserably
    0.43
    බ
    0.42
    垃圾
    0.42
     themselves
    0.41
     млн
    0.39
     deletes
    0.39
     wied
    0.39
    Activations Density 0.000%

    No Known Activations