© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6053
    Prev
    Next
    INDEX
    Explanations

    casting shadows and light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    sht
    1.27
     Sht
    1.27
    魍
    1.25
     smach
    1.25
     fabrica
    1.22
    mnop
    1.18
     subcontract
    1.17
     coût
    1.17
    waf
    1.16
     الالكتر
    1.14
    POSITIVE LOGITS
    ogan
    1.41
    isho
    1.19
    POINTS
    1.17
    adients
    1.13
     linéaires
    1.13
    ナム
    1.12
    egn
    1.12
    °,
    1.11
    lijn
    1.11
     Bieber
    1.10
    Activations Density 0.018%

    No Known Activations