© 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. 177810
    Prev
    Next
    INDEX
    Explanations

    depiction revealed

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

    appreciating and profitable items

    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
     pastures
    0.46
     खासकर
    0.44
     為
    0.43
    ina
    0.42
    itamins
    0.42
     Quebec
    0.42
    inen
    0.40
    utz
    0.40
     gardens
    0.40
     linens
    0.40
    POSITIVE LOGITS
     그림
    0.44
     mutil
    0.44
     dron
    0.42
    ಾಟ
    0.42
    ֥
    0.42
     depicted
    0.41
    上記の
    0.41
     mutilated
    0.41
    Dealer
    0.41
     depiction
    0.41
    Activations Density 0.001%

    No Known Activations