© 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. 53-GEMMASCOPE-2-RES-262K
    7. 49265
    Prev
    Next
    INDEX
    Explanations

    sexual availability

    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_53_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
     simplifié
    0.45
     Simpl
    0.41
     '\\;'
    0.40
     simpl
    0.40
     Simplifying
    0.39
     derrière
    0.39
     FB
    0.38
    奕
    0.38
     वेगवेगळ्या
    0.38
     simplification
    0.37
    POSITIVE LOGITS
     gas
    0.39
    Gas
    0.38
    성은
    0.38
     atomic
    0.38
     informants
    0.37
    agoza
    0.37
    性は
    0.36
    cesis
    0.36
     physicists
    0.36
    werden
    0.35
    Activations Density 0.000%

    No Known Activations