© 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. 46913
    Prev
    Next
    INDEX
    Explanations

    requires careful review

    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
    also
    0.49
    锜
    0.44
    łączy
    0.41
     பயிற்சிய
    0.41
     также
    0.41
     tiež
    0.41
    衵
    0.40
     also
    0.40
     Anche
    0.40
    빕
    0.40
    POSITIVE LOGITS
     निर्णय
    0.42
     devastation
    0.40
     cynicism
    0.40
     unchanged
    0.39
     ziel
    0.39
    gä
    0.39
     unprecedented
    0.38
     defiance
    0.38
     announcement
    0.38
    parency
    0.38
    Activations Density 0.005%

    No Known Activations