© 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. 252152
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     vajj
    0.54
     فَ
    0.52
    同時
    0.50
    leValue
    0.49
    㡀
    0.48
    }_{{\
    0.46
    cón
    0.46
     ហើយ
    0.45
     televisie
    0.45
    𝖔
    0.45
    POSITIVE LOGITS
    S
    0.55
     the
    0.50
     faced
    0.45
     Decoder
    0.44
     têm
    0.43
    H
    0.43
     Volume
    0.42
    E
    0.42
     esperti
    0.42
     of
    0.42
    Activations Density 0.002%

    No Known Activations