© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3790
    Prev
    Next
    INDEX
    Explanations

    language learning: grammar, listening, accuracy

    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_29_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
     monospace
    0.65
     cod
    0.65
     codebase
    0.65
     histidine
    0.64
     tink
    0.64
     opcode
    0.64
     primordial
    0.63
    朕
    0.63
    cod
    0.63
    uben
    0.62
    POSITIVE LOGITS
     Listening
    1.41
    Listening
    1.35
     listening
    1.28
     communicative
    1.26
     Grammar
    1.22
    listening
    1.19
     grammar
    1.18
    Gram
    1.15
     learner
    1.13
     learners
    1.13
    Activations Density 0.283%

    No Known Activations