© 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. 72228
    Prev
    Next
    INDEX
    Explanations

    big crowds, unique style, persistent symptoms

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

    geometric structures, human darkness, systems

    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
     gimmick
    0.45
    c
    0.42
     பிரத
    0.41
     site
    0.41
    KAT
    0.40
     pedir
    0.40
     gaming
    0.39
    kal
    0.38
    pah
    0.38
    kut
    0.38
    POSITIVE LOGITS
    अर
    0.50
    ື້ນ
    0.50
     अंडर
    0.49
    寤
    0.47
     सस्ते
    0.47
    🍥
    0.46
    यूपी
    0.46
    เมริกา
    0.46
     Numpy
    0.44
     Progression
    0.44
    Activations Density 0.001%

    No Known Activations