© 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. 188160
    Prev
    Next
    INDEX
    Explanations

    . or "March"

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

    female pornstar girlfriend

    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
     originale
    0.54
    )(
    0.53
    я
    0.52
    ài
    0.51
    ट
    0.50
     evento
    0.48
     probabilmente
    0.48
    疇
    0.47
    ),
    0.46
    ],
    0.45
    POSITIVE LOGITS
     ఆర్థిక
    0.52
    的网络
    0.47
     دي
    0.46
     يه
    0.45
     جما
    0.45
     مجموعه
    0.44
     一个
    0.44
     veřej
    0.44
    MemberList
    0.44
     ئۇ
    0.43
    Activations Density 0.001%

    No Known Activations