© 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-RES-262K
    7. 11103
    Prev
    Next
    INDEX
    Explanations

    unwanted sexual

    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
    }$.
    0.46
    。『
    0.45
    nYou
    0.42
     gating
    0.41
    <unused51>
    0.41
    。《
    0.41
     égard
    0.41
     CREATE
    0.40
    。<
    0.40
    there
    0.40
    POSITIVE LOGITS
     carbs
    0.44
     ramen
    0.44
     moisturizer
    0.43
     selfies
    0.42
     commute
    0.42
     allergies
    0.41
     Tinder
    0.41
     diet
    0.41
    喜欢的
    0.40
     pizza
    0.40
    Activations Density 0.069%

    No Known Activations