© 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. 73449
    Prev
    Next
    INDEX
    Explanations

    saintlyhood, negative energy, best security

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

    ethical considerations, taboo themes

    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
    τον
    0.51
    χν
    0.46
    ضمن
    0.46
    টিয়
    0.46
    は
    0.45
    किम
    0.44
    エア
    0.44
    mL
    0.44
    nullptr
    0.44
    PLATES
    0.44
    POSITIVE LOGITS
     беременности
    0.48
    ния
    0.47
     Singapore
    0.46
     жы
    0.46
     कामना
    0.46
     набу
    0.46
     Jewish
    0.45
    ỏ
    0.45
     crainte
    0.45
     cumple
    0.45
    Activations Density 0.000%

    No Known Activations