© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2693
    Prev
    Next
    INDEX
    Explanations

    sense of abstract states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     a
    0.81
     outro
    0.79
     app
    0.77
    quela
    0.76
     enige
    0.74
     otro
    0.74
     eine
    0.73
     Element
    0.73
     overlapped
    0.73
    esque
    0.72
    POSITIVE LOGITS
    pathetic
    1.15
    dozen
    0.95
     fech
    0.91
    兒
    0.85
    儿
    0.85
     few
    0.85
    venues
    0.84
    ulants
    0.83
    few
    0.82
     宮
    0.82
    Activations Density 0.407%

    No Known Activations