© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1171
    Prev
    Next
    INDEX
    Explanations

    non- prefix

    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_12_width_16k_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
    슭
    1.34
     sacs
    1.32
    같
    1.31
     shortness
    1.28
     Homes
    1.26
     despite
    1.23
     bride
    1.23
    asmuch
    1.23
    cald
    1.22
     cottages
    1.22
    POSITIVE LOGITS
    -
    2.26
    えた
    1.66
    -*
    1.65
    atives
    1.60
    слови
    1.58
    -'
    1.56
    acc
    1.55
    actives
    1.53
    -)
    1.52
    あれば
    1.52
    Activations Density 0.280%

    No Known Activations