© 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. 133075
    Prev
    Next
    INDEX
    Explanations

    Bonhoeffer

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

    baseload, statistical probabilities, environmental conditions

    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
    ﹡
    0.42
    )}(\
    0.42
    పి
    0.41
     wicked
    0.40
     workplace
    0.40
    ப்பூ
    0.40
    <0x80>
    0.39
     mitochondrial
    0.39
     flexible
    0.39
    }}(\
    0.39
    POSITIVE LOGITS
    midnight
    0.48
    夏の
    0.47
    原
    0.46
    leurs
    0.46
    堀
    0.46
    Light
    0.45
     Ecco
    0.45
     maje
    0.45
    Anon
    0.45
    Horizon
    0.45
    Activations Density 0.001%

    No Known Activations