© 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. 7099
    Prev
    Next
    INDEX
    Explanations

    not, but contrast

    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
    ANTE
    0.50
     underlies
    0.47
    administered
    0.47
    CompliancePolicy
    0.46
     製
    0.45
     contrasts
    0.45
     ಬೀ
    0.45
    েন্সি
    0.44
     solvents
    0.44
    liques
    0.44
    POSITIVE LOGITS
     Future
    0.50
    с
    0.50
     Anniversary
    0.48
    س
    0.47
     Out
    0.47
     Idee
    0.47
    ش
    0.47
     Comm
    0.46
     Landmark
    0.46
     Time
    0.46
    Activations Density 0.008%

    No Known Activations