© 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-65K
    7. 54878
    Prev
    Next
    INDEX
    Explanations

    business, tech, legal, and AI terms

    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
     verwend
    0.48
     vedere
    0.47
     blau
    0.47
     kleine
    0.47
     ஹ
    0.46
     kand
    0.45
     Tüm
    0.45
     ப
    0.45
     Mehr
    0.44
     numar
    0.44
    POSITIVE LOGITS
     Investor
    0.38
    Serializable
    0.38
    MenuInflater
    0.37
     Quaker
    0.37
    assertArg
    0.36
    üsseldorf
    0.35
    zuoye
    0.35
    staticmethod
    0.35
     governance
    0.34
    ponsor
    0.34
    Activations Density 0.107%

    No Known Activations