© 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. 1689
    Prev
    Next
    INDEX
    Explanations

    quantities and comparisons

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

    numbers following words like 'list of' or 'over'

    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
     þat
    0.40
    摖
    0.39
    躹
    0.34
    伡
    0.33
     لڑکی
    0.33
     erforderlich
    0.31
     آہستہ
    0.31
     সংশোধন
    0.31
     zdjęcie
    0.31
     사용
    0.30
    POSITIVE LOGITS
    3
    0.65
    5
    0.64
    1
    0.63
    4
    0.61
    8
    0.60
    7
    0.59
    6
    0.58
    2
    0.57
     hundreds
    0.54
     dozens
    0.54
    Activations Density 0.600%

    No Known Activations