© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108215
    Prev
    Next
    INDEX
    Explanations

    geometric operations on code structures

    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_34/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
    parken
    -1.09
    bedien
    -1.06
    haustible
    -1.02
     senhora
    -1.01
     mengucap
    -1.00
    ਖ਼
    -1.00
     šir
    -0.96
     saati
    -0.96
    Endereco
    -0.95
     își
    -0.95
    POSITIVE LOGITS
     orientation
    1.45
     edge
    1.37
     face
    1.30
     opposite
    1.27
    face
    1.20
     Face
    1.19
     faces
    1.19
     oriented
    1.18
     Orientation
    1.15
     connecting
    1.13
    Activations Density 0.015%

    No Known Activations