© 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. 191603
    Prev
    Next
    INDEX
    Explanations

    visiting places and people

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

    Alpaca model

    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
    炼
    0.49
     toekom
    0.48
    低于
    0.46
    ើរ
    0.45
     hallucin
    0.45
    াত
    0.42
    ας
    0.42
    είου
    0.42
    离开
    0.42
    。
    0.41
    POSITIVE LOGITS
    𝓻
    0.55
    アドレス
    0.50
     ショ
    0.50
    music
    0.50
    be
    0.48
    vand
    0.48
    lodge
    0.48
    vehicle
    0.48
    requency
    0.47
    rection
    0.47
    Activations Density 0.001%

    No Known Activations