© 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. 31-GEMMASCOPE-2-RES-262K
    7. 66059
    Prev
    Next
    INDEX
    Explanations

    required to or for

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

    ebook, common, datetime, converge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    :
    0.45
    ough
    0.44
     réception
    0.43
     maiden
    0.43
     recouvert
    0.42
    ’
    0.42
     countries
    0.41
    aling
    0.41
     norepinephrine
    0.41
    ných
    0.41
    POSITIVE LOGITS
     건축
    0.47
     작성
    0.46
    又は
    0.44
     대하여
    0.44
     כאשר
    0.44
    변경
    0.44
     මෙම
    0.43
    鸴
    0.43
    阖
    0.42
     直接
    0.42
    Activations Density 0.000%

    No Known Activations