© 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. 103928
    Prev
    Next
    INDEX
    Explanations

    earlobes, shares, operated, Sunday

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

    AI, skin, chicken, etc

    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
    rotz
    0.43
    繼續
    0.40
    कत
    0.38
    τι
    0.38
    addHandler
    0.38
    ]$.
    0.38
    と同様
    0.38
    வ்வாற
    0.38
    )}.
    0.38
     reissue
    0.37
    POSITIVE LOGITS
     اول
    0.51
    כּ
    0.46
     бути
    0.46
     בת
    0.46
    ช
    0.46
     ജൂ
    0.44
     ім
    0.44
    呼
    0.44
     جاس
    0.43
     досить
    0.43
    Activations Density 0.001%

    No Known Activations