© 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. 29-GEMMASCOPE-2-RES-65K
    7. 3350
    Prev
    Next
    INDEX
    Explanations

    positive descriptors

    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
     onboarding
    1.04
     lifecycle
    1.03
     miRNA
    0.98
     workflow
    0.97
    堃
    0.97
     blurry
    0.94
     groundbreaking
    0.93
     neuron
    0.93
     waveform
    0.93
     proactive
    0.92
    POSITIVE LOGITS
    ,--
    1.22
    ,—
    1.22
     forthwith
    1.12
    ;
    1.02
    ,-
    0.99
    --
    0.99
    indeed
    0.95
     likewise
    0.95
    '!
    0.95
    ."
    0.95
    Activations Density 0.106%

    No Known Activations