© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 89668
    Prev
    Next
    INDEX
    Explanations

    information technology systems

    np_acts-logits-general · gemini-2.5-flash-lite

    negation of physical action or destruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utility
    0.46
    highly
    0.46
    예
    0.46
    Proc
    0.45
    },\
    0.45
    Bd
    0.44
    maximal
    0.44
    Factor
    0.44
    much
    0.44
    ↵
    0.44
    POSITIVE LOGITS
     Soccer
    0.47
     Disputes
    0.45
     এখানে
    0.45
    上网
    0.43
     Sealed
    0.43
     tay
    0.43
     Seal
    0.42
     Astronomy
    0.42
     ș
    0.42
     aici
    0.41
    Activations Density 0.000%

    No Known Activations