© 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. 165104
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency or appearance

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

    introduce yourself and your career

    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
     mikro
    0.44
     植物
    0.44
     micro
    0.43
     ê
    0.41
     faint
    0.41
    }={\
    0.41
     dä
    0.41
     tropomyosin
    0.40
     cu
    0.40
     displayText
    0.39
    POSITIVE LOGITS
    ⒈
    0.53
    çamento
    0.52
    📪
    0.50
    jela
    0.50
    ⟦
    0.50
    ША
    0.48
    GX
    0.48
    Constructor
    0.47
    RID
    0.47
    Bola
    0.47
    Activations Density 0.001%

    No Known Activations