© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69418
    Prev
    Next
    INDEX
    Explanations

    whirring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    iscale
    1.47
    洎
    1.29
    etown
    1.27
    erdere
    1.27
    izable
    1.26
    anding
    1.25
    isjon
    1.23
    arita
    1.21
    匚
    1.20
     pSig
    1.13
    POSITIVE LOGITS
     buts
    2.04
     trom
    1.91
    rosc
    1.91
    ν
    1.91
    hab
    1.89
     iar
    1.87
    mern
    1.83
     které
    1.83
    min
    1.80
    ย
    1.79
    Activations Density 0.001%

    No Known Activations