© 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. 196060
    Prev
    Next
    INDEX
    Explanations

    street animals, home construction

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

    jumping from balconies

    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
    ia
    0.57
    A
    0.54
    helper
    0.52
    word
    0.49
    osi
    0.48
    models
    0.47
    da
    0.46
    obs
    0.46
    ifs
    0.46
    9
    0.46
    POSITIVE LOGITS
     terv
    0.57
     précision
    0.55
     reduzir
    0.54
     epistemology
    0.53
    ลิ
    0.52
    නී
    0.52
     cazul
    0.52
     masak
    0.52
     invariance
    0.50
    ન્મ
    0.50
    Activations Density 0.000%

    No Known Activations