© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 174458
    Prev
    Next
    INDEX
    Explanations

    children and adults

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers, currencies, and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hika
    0.49
    kapal
    0.45
     California
    0.43
     p
    0.43
    ޔ
    0.43
     bureaucratic
    0.42
     tayo
    0.42
     PVC
    0.41
     reinforcement
    0.41
     joe
    0.41
    POSITIVE LOGITS
    เด็ก
    0.51
     děti
    0.48
    成年
    0.48
    平均
    0.47
    崢
    0.46
    细腻
    0.46
     الأطفال
    0.46
     adultes
    0.45
     Adults
    0.45
     étendue
    0.44
    Activations Density 0.001%

    No Known Activations