© 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. 10348
    Prev
    Next
    INDEX
    Explanations

    small

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

    smallness

    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
     współ
    0.62
    ન્મ
    0.61
    Ц
    0.58
    આ
    0.55
    ामान्य
    0.54
    ك
    0.53
    Გ
    0.53
    ਮ
    0.53
    淐
    0.53
    Tổng
    0.52
    POSITIVE LOGITS
     small
    1.41
    small
    1.40
    小的
    1.36
     pequeña
    1.35
     pequeñas
    1.30
     pequeño
    1.23
    Small
    1.22
     pequena
    1.21
     pequeños
    1.20
     piccoli
    1.20
    Activations Density 0.164%

    No Known Activations