© 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. 57814
    Prev
    Next
    INDEX
    Explanations

    stripping strings

    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
    ০
    0.48
     yatha
    0.46
    š
    0.45
    ல
    0.43
    מו
    0.41
     yath
    0.41
    ன
    0.41
    து
    0.40
     Return
    0.40
    ");</
    0.40
    POSITIVE LOGITS
    字母
    0.54
     peculiarities
    0.46
    。
    0.45
     当
    0.45
     категорії
    0.44
     cest
    0.44
     indicato
    0.44
    letters
    0.44
     paréntesis
    0.43
     coke
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.