© 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. 251020
    Prev
    Next
    INDEX
    Explanations

    announcements, plans, or instructions

    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
    通販
    0.44
    yoruz
    0.43
     rediscovered
    0.42
    窺
    0.42
    E
    0.41
     imparted
    0.40
    也都
    0.40
    kami
    0.40
    pues
    0.40
    ongi
    0.39
    POSITIVE LOGITS
     médian
    0.49
    规划
    0.48
     Pendleton
    0.47
     geplant
    0.46
    级别的
    0.46
     سخت
    0.46
    铭
    0.46
    ależy
    0.45
    HARD
    0.45
    频繁
    0.45
    Activations Density 0.000%

    No Known Activations