© 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. 146080
    Prev
    Next
    INDEX
    Explanations

    age categories

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

    extremely explicit and graphic

    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
     dingen
    0.49
     εν
    0.49
     tieto
    0.49
     很
    0.47
     人気
    0.47
     suma
    0.47
     を
    0.46
     সমিতির
    0.46
    倉
    0.46
    圓
    0.46
    POSITIVE LOGITS
     age
    0.49
     synonymous
    0.48
     wildest
    0.48
     baton
    0.48
     repercussions
    0.47
     allocated
    0.47
     demarc
    0.46
     classificação
    0.45
     arbitration
    0.45
     arbit
    0.45
    Activations Density 0.000%

    No Known Activations