© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 42954
    Prev
    Next
    INDEX
    Explanations

    followed/following [company/program name]

    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
    ০
    1.23
    ae
    1.20
    רו
    1.20
    いです
    1.19
    ৫
    1.18
    ’
    1.16
    ৮
    1.16
     ∼
    1.15
     имеется
    1.14
    0
    1.14
    POSITIVE LOGITS
    𝒔
    1.34
    ী
    1.30
    𝒖
    1.27
    n
    1.23
    d
    1.20
     Interess
    1.20
     sami
    1.19
    bani
    1.17
    ක්ෂ
    1.15
     sien
    1.15
    Activations Density 0.001%

    No Known Activations