© 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. 169007
    Prev
    Next
    INDEX
    Explanations

    contact numbers, links, names

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

    relationship, billion, platforms, unconscious, common, perspective, fetish, surprise

    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
     retrospective
    0.49
     받
    0.46
     ब्लैक
    0.46
     ಇದರಿಂದ
    0.45
    сцю
    0.44
     വഹ
    0.44
     น้อง
    0.44
    んに
    0.43
    艨
    0.42
     오는
    0.42
    POSITIVE LOGITS
     Extremely
    0.46
     Suggested
    0.46
     you
    0.44
    র্ম
    0.44
     bình
    0.44
    সূ
    0.43
     proprietà
    0.43
    ត្រ
    0.42
     Yardım
    0.42
    теля
    0.41
    Activations Density 0.000%

    No Known Activations