© 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. 98062
    Prev
    Next
    INDEX
    Explanations

    introduces named entity or topic

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

    ** , plum, branding, gig, peony, segmentation, addition, Group

    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
     statesmen
    0.49
     unmet
    0.47
     obscured
    0.46
     pith
    0.46
    izante
    0.46
    棂
    0.46
     artistic
    0.45
     materiales
    0.44
     materials
    0.44
     informations
    0.43
    POSITIVE LOGITS
    ÇA
    0.56
    Ç
    0.54
    çar
    0.49
    ç
    0.45
     ç
    0.45
    forestation
    0.45
    Ça
    0.45
     সর্বোচ্চ
    0.44
     présentée
    0.44
    PROTE
    0.44
    Activations Density 0.000%

    No Known Activations