© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 222125
    Prev
    Next
    INDEX
    Explanations

    sexual stimulation and email address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     específica
    0.38
     bookmarks
    0.38
    劉
    0.38
     বিব্রত
    0.38
     ephemeral
    0.37
     वाकई
    0.37
     afterPath
    0.36
     catastrophes
    0.36
     reviewing
    0.35
    プチ
    0.35
    POSITIVE LOGITS
    객
    0.46
    geke
    0.41
     mnoho
    0.40
    OBJ
    0.40
    ಳ್
    0.39
    ಿದ್ದಾನೆ
    0.39
    ALLOW
    0.38
    orr
    0.37
    indler
    0.37
    Significant
    0.36
    Activations Density 0.000%

    No Known Activations