© 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. 124932
    Prev
    Next
    INDEX
    Explanations

    series and service manuals

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

    options ranging in formality

    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
    le
    0.50
     Featured
    0.50
    domain
    0.49
    PS
    0.48
    Fs
    0.48
    s
    0.48
    ps
    0.47
    XE
    0.46
     STATEMENT
    0.46
     ℝ
    0.46
    POSITIVE LOGITS
     вероят
    0.47
     podía
    0.46
     administração
    0.46
     jugado
    0.45
     probabilidad
    0.45
     contrived
    0.45
    вающей
    0.45
    㴓
    0.44
    ंदोल
    0.44
    лык
    0.44
    Activations Density 0.001%

    No Known Activations