© 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. 228874
    Prev
    Next
    INDEX
    Explanations

    medical applications, garbage, packaging

    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
    IN
    0.59
    ر
    0.58
    할
    0.53
    في
    0.51
    З
    0.50
    SEL
    0.49
    O
    0.49
     vyroben
    0.48
    하지
    0.48
    和
    0.48
    POSITIVE LOGITS
     проте
    0.48
     glo
    0.45
     munic
    0.44
     gripper
    0.43
     discretion
    0.43
     crise
    0.43
     scoperta
    0.43
     reaffirm
    0.43
     packaging
    0.43
     topology
    0.42
    Activations Density 0.000%

    No Known Activations