© 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-65K
    7. 61768
    Prev
    Next
    INDEX
    Explanations

    piercings, belly button, specific details

    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_65k_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
    Below
    0.44
    escol
    0.40
     alternativa
    0.38
     euer
    0.37
    琀
    0.37
    SK
    0.36
     inkluder
    0.36
    Sen
    0.35
     coste
    0.35
    닿
    0.35
    POSITIVE LOGITS
    ैल
    0.46
    чам
    0.45
     גי
    0.45
     आलेल्या
    0.44
     billing
    0.43
     salsa
    0.43
    ື່
    0.42
    ృష్
    0.42
    㬰
    0.41
    ánica
    0.41
    Activations Density 0.035%

    No Known Activations