© 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. 67405
    Prev
    Next
    INDEX
    Explanations

    Christmas, coffee, pixel specific items

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

    established techniquesubconscious mindindividual financialselection pressureDraw on cardconfidence

    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
     아직
    0.49
     Nuest
    0.48
    ገለ
    0.44
    с
    0.44
     Fabrics
    0.44
    明確
    0.43
     다음
    0.42
    션을
    0.42
     них
    0.42
     Procurement
    0.42
    POSITIVE LOGITS
     armado
    0.44
     sciatica
    0.43
     brasileiro
    0.42
     exercise
    0.42
     syph
    0.40
    وذ
    0.40
    छा
    0.40
    </tr>
    0.40
     wojewód
    0.39
     forests
    0.39
    Activations Density 0.001%

    No Known Activations