© 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. 31-GEMMASCOPE-2-RES-262K
    7. 83079
    Prev
    Next
    INDEX
    Explanations

    detailed sexual descriptions

    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_31_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
    zigen
    0.49
    িয়াম
    0.45
    𝐶
    0.44
    EndTime
    0.44
     час
    0.44
     жүкт
    0.44
    ЕМ
    0.44
    берём
    0.43
     woolen
    0.43
    VideoStream
    0.43
    POSITIVE LOGITS
    the
    0.49
    _
    0.45
    ophan
    0.43
     간
    0.42
    รอง
    0.41
    हा
    0.41
    ha
    0.40
    ils
    0.40
    ressant
    0.40
     continua
    0.39
    Activations Density 0.009%

    No Known Activations