© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 148715
    Prev
    Next
    INDEX
    Explanations

    telekinesis and telepathy

    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
     Juniors
    0.67
    SOLUTION
    0.66
    ʒ
    0.62
    inhos
    0.61
     solution
    0.61
    gnię
    0.60
    ‰
    0.59
     ε
    0.59
     summation
    0.58
    ွှ
    0.58
    POSITIVE LOGITS
     pergi
    0.88
     kendaraan
    0.77
     berpikir
    0.74
    ísica
    0.72
    sehen
    0.71
    atis
    0.71
     বলল
    0.70
     lesen
    0.68
     souten
    0.68
     típ
    0.68
    Activations Density 0.000%

    No Known Activations