© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10657
    Prev
    Next
    INDEX
    Explanations

    and cash, playing Brazil, LED, other operations

    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_9_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
    தல்
    1.14
     đỡ
    1.11
    ં
    1.11
    maid
    1.09
    iertas
    1.08
    lač
    1.08
    ya
    1.07
     pulgadas
    1.06
    ּ
    1.06
     rays
    1.05
    POSITIVE LOGITS
    ার
    1.45
    謬
    1.21
    eras
    1.20
    erar
    1.19
    ٹری
    1.16
    中村
    1.15
     progressBar
    1.15
     assistive
    1.15
     copertura
    1.14
    ینګ
    1.14
    Activations Density 0.000%

    No Known Activations