© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54398
    Prev
    Next
    INDEX
    Explanations

    export class, meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loadFile
    0.48
     ត
    0.44
     ambientale
    0.44
    ອາຫານ
    0.43
     좋아하는
    0.42
    व्यक्तित्व
    0.41
    pèce
    0.41
    悹
    0.41
    humidité
    0.40
     mayhem
    0.40
    POSITIVE LOGITS
    bridges
    0.40
    Validity
    0.40
    Archer
    0.39
     secreto
    0.38
     jumpa
    0.38
     irr
    0.37
    Said
    0.37
     cuyos
    0.37
    akir
    0.36
    Robin
    0.36
    Activations Density 0.001%

    No Known Activations