© 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. 34-GEMMASCOPE-RES-131K
    7. 64247
    Prev
    Next
    INDEX
    Explanations

    phrase initiation

    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
    ætter
    -0.96
    ㄋ
    -0.95
    シン
    -0.94
     Corde
    -0.84
    ⠙
    -0.83
    ishments
    -0.81
    IFORM
    -0.81
     prejudicial
    -0.81
    richtet
    -0.80
     extrêmement
    -0.80
    POSITIVE LOGITS
    ʃ
    0.99
     gotten
    0.91
     kinds
    0.91
     researcher
    0.90
     writer
    0.85
     dealing
    0.85
     though
    0.82
     TOEFL
    0.79
    getElementsBy
    0.79
     belonged
    0.79
    Activations Density 0.007%

    No Known Activations