© 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. 35677
    Prev
    Next
    INDEX
    Explanations

    the Almighty, Home Occupation, time

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

    automatic rinsing; ADCU

    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
     avatars
    0.50
     dazzling
    0.47
     conundrum
    0.46
    >
    0.46
     incongru
    0.46
     barbec
    0.46
     alluded
    0.45
     rew
    0.44
     jarring
    0.44
    ๊
    0.43
    POSITIVE LOGITS
     patip
    0.60
    rester
    0.48
    lern
    0.47
    用
    0.47
    мія
    0.47
     роз
    0.46
    anum
    0.46
    halen
    0.46
    ректор
    0.46
    㴬
    0.46
    Activations Density 0.000%

    No Known Activations