© 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. 41-GEMMASCOPE-2-RES-262K
    7. 26382
    Prev
    Next
    INDEX
    Explanations

    Sixty, Fifty, Forty, Seventy, Eighty

    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_all/layer_41_width_262k_l0_big
    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
     cues
    0.43
    selectors
    0.40
     beeindruck
    0.40
     म्युच्युअल
    0.39
     surnames
    0.39
     neun
    0.39
    拃
    0.38
    ох
    0.38
    atinum
    0.37
    第九
    0.37
    POSITIVE LOGITS
     Sixty
    0.84
     CBS
    0.78
    CBS
    0.75
     sixty
    0.70
     Fifty
    0.55
     ABC
    0.53
     Forty
    0.53
     Seventy
    0.53
     Eighty
    0.51
     Dat
    0.50
    Activations Density 0.001%

    No Known Activations