© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 491
    Prev
    Next
    INDEX
    Explanations

    and in

    np_acts-logits-general · gemini-2.5-flash-lite

    and

    np_acts-logits-general · gemini-2.5-flash-lite

    and

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_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
    ль
    0.45
    νο
    0.44
     demás
    0.43
    v
    0.43
    执行
    0.43
    ні
    0.42
    "/"
    0.42
    ز
    0.41
    -
    0.41
    ua
    0.40
    POSITIVE LOGITS
     i
    0.55
    Iraq
    0.48
    Ꮳ
    0.47
     it
    0.46
     a
    0.46
    Eight
    0.45
    arid
    0.45
    A
    0.45
    Several
    0.44
     unsuccessfully
    0.44
    Activations Density 0.229%

    No Known Activations