© 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. 116854
    Prev
    Next
    INDEX
    Explanations

    a fourth

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

    forbidden, prohibited, resistance

    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
     Homo
    0.46
     Homeless
    0.46
    쌀
    0.45
     Homestead
    0.43
     Mr
    0.43
     HELP
    0.43
     Ms
    0.41
    ь
    0.41
    skill
    0.41
     Pilgr
    0.40
    POSITIVE LOGITS
    㓦
    0.53
    EYER
    0.52
    녈
    0.52
     możemy
    0.49
    etro
    0.48
     établ
    0.47
    য়াল
    0.47
     dentées
    0.46
     neun
    0.46
    υτό
    0.45
    Activations Density 0.001%

    No Known Activations