© 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. 54330
    Prev
    Next
    INDEX
    Explanations

    Selling Cars, perfect for

    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
    茠
    0.52
     TAK
    0.51
     loom
    0.49
     Taking
    0.49
     inhoud
    0.49
    푝
    0.48
     terapi
    0.48
     võivad
    0.48
     vä
    0.48
     vše
    0.47
    POSITIVE LOGITS
     stunned
    0.46
     accompanied
    0.45
    blit
    0.45
     recruited
    0.41
    Blitz
    0.41
    ↵↵↵↵↵↵↵↵
    0.40
     lashed
    0.40
    λει
    0.40
    ]<?
    0.40
     tuned
    0.39
    Activations Density 0.003%

    No Known Activations