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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 111506
    Prev
    Next
    INDEX
    Explanations

    light filtering through dust motes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     ܗ
    0.51
     చూ
    0.47
     ہ
    0.45
    Р
    0.44
    Training
    0.43
     trainings
    0.43
     शिक
    0.43
    Some
    0.42
     ر
    0.42
    ation
    0.42
    POSITIVE LOGITS
    plo
    0.47
    olutamente
    0.46
     plástico
    0.45
    <0xB5>
    0.44
     અમારા
    0.44
     wiped
    0.43
     drank
    0.42
     plummeted
    0.41
     milhares
    0.41
     stabbed
    0.40
    Activations Density 0.014%

    No Known Activations