© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151997
    Prev
    Next
    INDEX
    Explanations

    commensurate with other items

    np_acts-logits-general · gemini-2.5-flash-lite

    sexual acts and their considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     精
    0.50
     어려
    0.49
    精
    0.47
    GetLength
    0.44
    科學
    0.43
    нена
    0.42
    拔
    0.42
     meisten
    0.42
    保健
    0.42
     মের
    0.42
    POSITIVE LOGITS
     समानता
    0.47
     commensurate
    0.46
     textured
    0.45
    zion
    0.45
     believable
    0.45
    ument
    0.45
     equivalents
    0.44
    –
    0.44
     solicit
    0.43
     devo
    0.43
    Activations Density 0.006%

    No Known Activations