© 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. 24-GEMMASCOPE-2-RES-262K
    7. 11586
    Prev
    Next
    INDEX
    Explanations

    since month/date

    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_24_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
    0
    0.58
    5
    0.54
    1
    0.52
    8
    0.50
     superstition
    0.49
    3
    0.47
    אי
    0.45
    9
    0.45
    6
    0.44
    Ι
    0.42
    POSITIVE LOGITS
    宣布
    0.56
    umumkan
    0.56
     annoncé
    0.55
    ونز
    0.54
     tomonidan
    0.53
     hotly
    0.53
     três
    0.52
     několik
    0.52
     fyra
    0.52
     beberapa
    0.51
    Activations Density 0.001%

    No Known Activations