© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35337
    Prev
    Next
    INDEX
    Explanations

    dust motes, dust blooms, dust bunnies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ב
    2.06
    сний
    1.82
    л
    1.80
    ر
    1.76
    င်း
    1.75
    きた
    1.73
    ू
    1.73
    ిన
    1.70
    र
    1.70
    lt
    1.64
    POSITIVE LOGITS
    y
    2.31
    s
    2.27
    िक
    2.02
    ात
    1.98
    ap
    1.94
    yra
    1.84
    sight
    1.81
    sair
    1.80
    งาน
    1.79
    satz
    1.79
    Activations Density 0.004%

    No Known Activations