© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2885
    Prev
    Next
    INDEX
    Explanations

    causes and reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ically
    2.93
    िक
    2.84
    د
    2.82
     spus
    2.78
    ringa
    2.78
     दूसरी
    2.76
    ্নের
    2.75
    ्त
    2.68
    ордина
    2.65
    ajos
    2.61
    POSITIVE LOGITS
    <bos>
    4.51
     diligence
    2.64
    হের
    2.56
    ے
    2.51
    ▋
    2.46
    𝕝
    2.45
    ગ
    2.45
    χω
    2.39
     heir
    2.39
    դ
    2.38
    Activations Density 0.025%

    No Known Activations