© 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. 10293
    Prev
    Next
    INDEX
    Explanations

    explanation

    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
     lucru
    1.07
    ం
    1.05
    t
    1.01
    (\
    0.99
    லோச
    0.93
    م
    0.92
    会有
    0.92
    деся
    0.91
    бычно
    0.90
    ப்
    0.90
    POSITIVE LOGITS
    מ
    1.05
     Gł
    1.03
    हा
    1.01
    ética
    0.98
     Employers
    0.95
     surviving
    0.95
     Microphone
    0.93
     Immunohist
    0.92
    ột
    0.92
    strokes
    0.91
    Activations Density 0.014%

    No Known Activations