© 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. 195130
    Prev
    Next
    INDEX
    Explanations

    age verification, parental consent

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

    existential states and discoveries

    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
     with
    0.45
     consecutivos
    0.44
     WITH
    0.44
     slut
    0.43
    َص
    0.43
     عندك
    0.41
     gutter
    0.41
    有力
    0.41
    單
    0.41
     eut
    0.40
    POSITIVE LOGITS
     bislang
    0.55
    ewöhn
    0.53
     এলাম
    0.51
    花了
    0.47
    تباين
    0.46
     আপাতত
    0.46
     시험
    0.46
     চৈ
    0.44
     heretofore
    0.44
    lerini
    0.43
    Activations Density 0.000%

    No Known Activations