© 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. 14885
    Prev
    Next
    INDEX
    Explanations

    digits followed by periods

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

    numbers or identifiers followed by punctuation

    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
    8
    0.48
    ों
    0.47
    rätt
    0.47
    اد
    0.46
    9
    0.46
    <unused311>
    0.45
     इन्वेस्ट
    0.45
    ಾವ
    0.45
    orduk
    0.45
    <unused303>
    0.45
    POSITIVE LOGITS
    .-
    0.47
     그의
    0.43
    .??
    0.43
    ॰
    0.42
     minuscule
    0.41
    โ
    0.41
     .
    0.41
     своїх
    0.40
     defenseman
    0.40
    .[[
    0.40
    Activations Density 0.127%

    No Known Activations