© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3141
    Prev
    Next
    INDEX
    Explanations

    It's not like

    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
     LastName
    1.20
     kroner
    1.11
    svelte
    1.09
    hopper
    1.05
    轳
    1.05
    s
    1.02
    Basket
    1.02
    ONDER
    1.02
    CHREIB
    1.01
    B
    1.01
    POSITIVE LOGITS
    larda
    1.25
    шої
    1.19
    ための
    1.17
    ا
    1.16
    お金
    1.13
     будто
    1.13
    larni
    1.12
    אן
    1.11
     나서
    1.09
    かっこ
    1.09
    Activations Density 0.007%

    No Known Activations