© 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-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220377
    Prev
    Next
    INDEX
    Explanations

    sex drive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
    খিল
    0.38
    acceptable
    0.36
    Ầ
    0.35
    Validator
    0.35
     boys
    0.35
    taş
    0.34
     validations
    0.34
    墙
    0.34
     Closeup
    0.33
     CE
    0.33
    POSITIVE LOGITS
     మహిళ
    0.40
     Tiber
    0.39
     rapidity
    0.38
     உள்ளது
    0.36
     женщи
    0.36
     thỏa
    0.36
     महिला
    0.35
    嚮
    0.35
     મહિલા
    0.35
     प्रस्तु
    0.35
    Activations Density 0.003%

    No Known Activations