© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5650
    Prev
    Next
    INDEX
    Explanations

    is or isa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     हों
    0.91
    hills
    0.82
     मिले
    0.81
     Take
    0.81
     împre
    0.78
    以
    0.77
    עם
    0.75
     các
    0.75
    take
    0.74
     entail
    0.74
    POSITIVE LOGITS
     뭔
    1.06
    abella
    1.05
     féidir
    1.05
    뭔
    1.00
    abelle
    1.00
    uzu
    0.99
    RAEL
    0.98
    lands
    0.96
    abel
    0.95
    cellaneous
    0.90
    Activations Density 0.037%

    No Known Activations