© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 175292
    Prev
    Next
    INDEX
    Explanations

    email accounts

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

    dates and times

    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
     考え
    0.47
     الشمس
    0.47
    scrollHeight
    0.44
    overline
    0.42
     শাস্ত্র
    0.42
     покупки
    0.42
     buồn
    0.41
    _{+}-
    0.40
     Baroque
    0.40
    ^*_{
    0.40
    POSITIVE LOGITS
    E
    0.44
    Q
    0.44
    en
    0.43
    cía
    0.42
    rem
    0.40
    ING
    0.40
    cnpj
    0.40
     state
    0.40
    state
    0.39
    rés
    0.39
    Activations Density 0.001%

    No Known Activations