© 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-262K
    7. 145749
    Prev
    Next
    INDEX
    Explanations

    mysteries, knowledge, fears, dreams, feelings reside

    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
     tél
    0.71
     eag
    0.70
    भाव
    0.68
     Architektur
    0.66
     パ
    0.66
     vab
    0.65
    <unused398>
    0.64
     dépens
    0.63
    橛
    0.63
     verte
    0.63
    POSITIVE LOGITS
     intran
    0.74
     interleaved
    0.73
     injections
    0.73
    Injection
    0.72
    Жи
    0.72
    ्रमण
    0.70
    luoromethyl
    0.70
    subscribed
    0.70
     ascribed
    0.70
     intramolecular
    0.70
    Activations Density 0.001%

    No Known Activations