© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8837
    Prev
    Next
    INDEX
    Explanations

    css styling and coding snippets

    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_40_width_16k_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
     impressive
    0.40
     allegations
    0.39
     ="
    0.39
     Ehe
    0.38
     連
    0.38
     claim
    0.38
     Dirac
    0.38
     Speech
    0.37
    Dirac
    0.37
    "{
    0.37
    POSITIVE LOGITS
    鹏
    0.41
    urgie
    0.41
    vastatin
    0.41
    cstring
    0.39
    েম্বর
    0.39
     stargazerCount
    0.38
     চক্র
    0.37
     العاش
    0.37
    几天
    0.37
     cerevisiae
    0.37
    Activations Density 0.027%

    No Known Activations