© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128370
    Prev
    Next
    INDEX
    Explanations

    school and graduation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     —
    -1.26
     to
    -1.23
     already
    -1.12
    ↵↵
    -1.00
     HttpNotFound
    -0.96
     zostać
    -0.93
    setString
    -0.93
    łop
    -0.91
     使用
    -0.91
     risking
    -0.91
    POSITIVE LOGITS
    💠
    1.12
     amélior
    1.09
     sambung
    1.08
    猹
    1.06
    bildning
    1.04
     SYDNEY
    1.04
    tabil
    1.03
     multe
    1.03
    ︓
    1.02
     そば
    1.01
    Activations Density 0.020%

    No Known Activations