© 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. 41124
    Prev
    Next
    INDEX
    Explanations

    speech attributed to

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

    bullet points starting with capitalized words

    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
    し
    0.52
    є
    0.52
    ך
    0.51
    ான்
    0.50
    ին
    0.48
    зан
    0.47
    եմ
    0.47
    는
    0.45
    อร์
    0.44
    デイ
    0.44
    POSITIVE LOGITS
    vollen
    0.56
    il
    0.55
    et
    0.54
     अवलंब
    0.51
    ಗೊಂಡ
    0.50
     sorti
    0.49
    on
    0.48
     nächsten
    0.48
     अनुभूति
    0.47
    at
    0.47
    Activations Density 0.007%

    No Known Activations