© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47401
    Prev
    Next
    INDEX
    Explanations

    are followed by example of

    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
     otherworldly
    0.50
     kabhi
    0.47
     توانند
    0.47
    🫢
    0.45
    🥸
    0.45
     ඒවා
    0.44
     tür
    0.43
    ামুটি
    0.43
     بە
    0.43
     increí
    0.42
    POSITIVE LOGITS
     Best
    0.41
     Closing
    0.41
     CO
    0.40
     ¬
    0.40
     this
    0.40
     HT
    0.39
     TP
    0.38
     Jon
    0.38
     Register
    0.38
     Good
    0.37
    Activations Density 0.033%

    No Known Activations