© 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. 71805
    Prev
    Next
    INDEX
    Explanations

    either expressed or implied

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

    body attributes

    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
    леко
    0.47
    cence
    0.47
    载
    0.47
    discharge
    0.46
    برى
    0.46
    erté
    0.45
    nění
    0.44
    橹
    0.44
    قابل
    0.43
    лично
    0.43
    POSITIVE LOGITS
     今天
    0.49
     GMO
    0.45
    S
    0.44
     round
    0.44
    EO
    0.43
     vuoden
    0.42
    N
    0.42
    O
    0.42
     EO
    0.41
    ano
    0.41
    Activations Density 0.000%

    No Known Activations