© 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
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149523
    Prev
    Next
    INDEX
    Explanations

    0 file permissions

    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_29_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
     Surely
    0.75
    Surely
    0.66
    esu
    0.65
    なん
    0.65
    TextureAsset
    0.64
    荪
    0.63
    艰
    0.63
    蠵
    0.62
    atism
    0.62
    끝
    0.62
    POSITIVE LOGITS
     olhar
    0.68
     retirada
    0.67
    रण
    0.67
     trente
    0.67
    apj
    0.63
    drž
    0.62
    畦
    0.62
     escolha
    0.62
     rota
    0.61
     obtenir
    0.60
    Activations Density 0.005%

    No Known Activations