© 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-262K
    7. 148189
    Prev
    Next
    INDEX
    Explanations

    describing states or characteristics

    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_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
    டியான
    0.69
    hito
    0.67
    tale
    0.65
    seudo
    0.62
    cosx
    0.60
    countplot
    0.59
    $/.
    0.59
     serat
    0.59
    tosecond
    0.58
    क्रोस
    0.58
    POSITIVE LOGITS
     geboren
    0.85
     able
    0.77
     alike
    0.77
    摸
    0.77
    骓
    0.76
     attracted
    0.75
     affected
    0.73
     bom
    0.73
     유
    0.71
     felices
    0.71
    Activations Density 0.018%

    No Known Activations