© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4812
    Prev
    Next
    INDEX
    Explanations

    National Alliance on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
     Bağ
    0.83
    กร
    0.81
    प्या
    0.74
    enov
    0.74
    Escol
    0.73
    зили
    0.73
    철
    0.72
    Hed
    0.72
     vált
    0.72
    ޤ
    0.71
    POSITIVE LOGITS
     Against
    1.00
     against
    0.82
     closer
    0.76
    ર્ચ
    0.74
     массива
    0.70
    垒
    0.70
     stigmat
    0.68
    认为
    0.68
     stressed
    0.68
    ὺς
    0.67
    Activations Density 0.025%

    No Known Activations