© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 18833
    Prev
    Next
    INDEX
    Explanations

    location or starting position

    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_22_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
     கூட்டம்
    0.69
    ének
    0.68
     기대
    0.67
    itimate
    0.67
     Struktur
    0.66
    畑
    0.66
    間に
    0.66
    ޅ
    0.65
    [\
    0.65
     ciągu
    0.64
    POSITIVE LOGITS
     where
    2.10
    Where
    1.99
     donde
    1.98
     Where
    1.96
    where
    1.84
     WHERE
    1.70
    WHERE
    1.69
     où
    1.69
     där
    1.54
     حيث
    1.49
    Activations Density 0.032%

    No Known Activations