© 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. 62784
    Prev
    Next
    INDEX
    Explanations

    multiple versions

    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
    壶
    0.51
    מו
    0.48
    贷款
    0.48
     microp
    0.48
     wody
    0.48
     waters
    0.47
     pagamento
    0.47
     CONT
    0.47
     Ausland
    0.46
    芽
    0.46
    POSITIVE LOGITS
     theorists
    0.52
    iz
    0.50
    think
    0.46
    tion
    0.45
    im
    0.44
    imist
    0.44
    íz
    0.44
    stag
    0.44
    tn
    0.44
    isz
    0.43
    Activations Density 0.004%

    No Known Activations