© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11382
    Prev
    Next
    INDEX
    Explanations

    eager to learn or contribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    Título
    2.30
    ".$
    2.28
    نس
    2.27
    ὔ
    2.27
    бен
    2.23
    ίνη
    2.21
    ierte
    2.21
    ὗ
    2.17
    μοσ
    2.15
    ὐ
    2.15
    POSITIVE LOGITS
    ي
    2.60
    م
    2.56
    ্ণ
    2.49
    eal
    2.44
    o
    2.43
    e
    2.41
    ﻢ
    2.39
    л
    2.38
    м
    2.37
    ating
    2.23
    Activations Density 0.086%

    No Known Activations