© 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. 2594
    Prev
    Next
    INDEX
    Explanations

    exploring themes of

    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
    bero
    1.40
     cognac
    1.29
    嗖
    1.28
    歇
    1.28
     naam
    1.25
     drib
    1.25
     poudre
    1.24
    وتي
    1.24
     nume
    1.24
    잠
    1.22
    POSITIVE LOGITS
     towards
    1.66
    towards
    1.62
     toward
    1.40
     against
    1.27
     parallels
    1.25
     AGAINST
    1.22
    Against
    1.21
    Towards
    1.17
     Towards
    1.16
     αντι
    1.15
    Activations Density 0.106%

    No Known Activations