© 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. 157345
    Prev
    Next
    INDEX
    Explanations

    point of commencement

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

    breakthrough easily three here code is

    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
     तित
    0.54
    дини
    0.48
     поту
    0.47
     κινη
    0.45
     زر
    0.45
    URER
    0.45
     赤
    0.44
     રંગ
    0.44
    を設定
    0.44
     pulver
    0.43
    POSITIVE LOGITS
    䒠
    0.46
    m
    0.44
     documents
    0.43
    내는
    0.42
     currents
    0.42
    hs
    0.41
    h
    0.41
     TypeScript
    0.41
    <?=
    0.40
    믈
    0.40
    Activations Density 0.003%

    No Known Activations