© 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. 107598
    Prev
    Next
    INDEX
    Explanations

    locations and specific terms

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

    discharging fully, student attendance

    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
     눈
    0.48
     Taille
    0.47
     حی
    0.47
    颦
    0.46
     الخمسه
    0.45
     snub
    0.45
     七
    0.43
     얘는
    0.43
     얘
    0.43
     MERCHANT
    0.43
    POSITIVE LOGITS
    Vinyl
    0.54
    aluminum
    0.52
    א
    0.51
    am
    0.50
    captivity
    0.49
    vinyl
    0.48
    ική
    0.47
    entertain
    0.46
    ਅ
    0.46
    Aluminum
    0.45
    Activations Density 0.001%

    No Known Activations