© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11678
    Prev
    Next
    INDEX
    Explanations

    clause, emphasis, preconditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_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
    юць
    1.56
    у
    1.53
    icier
    1.51
    ter
    1.42
    ай
    1.40
    ifico
    1.39
    ‍♀
    1.34
     interstices
    1.34
     bloquear
    1.32
    ো
    1.28
    POSITIVE LOGITS
     overrides
    1.43
    ivity
    1.38
     holog
    1.35
    redu
    1.33
    केवल
    1.31
     понимать
    1.31
     phenotype
    1.30
    द्धि
    1.27
    Initialized
    1.27
    yce
    1.25
    Activations Density 0.000%

    No Known Activations