© 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-65K
    7. 54962
    Prev
    Next
    INDEX
    Explanations

    issues and constraints

    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_65k_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
    سی
    0.51
    р
    0.43
    ง
    0.43
     Olivia
    0.42
    为了
    0.42
     bolog
    0.40
     searing
    0.40
    ం
    0.40
     SEA
    0.40
     whos
    0.40
    POSITIVE LOGITS
     vitesses
    0.50
    tych
    0.46
     Commentaires
    0.45
     junt
    0.44
     |
    0.44
    ATTA
    0.43
    _
    0.43
     гэта
    0.43
    –
    0.43
     œufs
    0.43
    Activations Density 0.001%

    No Known Activations