© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36050
    Prev
    Next
    INDEX
    Explanations

    direction and orientation

    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
     πάν
    -1.20
    וּ
    -1.20
    Современ
    -1.20
    توضیحات
    -1.16
    וּ
    -1.12
    ̳
    -1.11
    entant
    -1.10
    EndInit
    -1.08
    tehen
    -1.08
    深圳
    -1.06
    POSITIVE LOGITS
     direction
    1.22
     directions
    1.06
    gencias
    1.05
     orientation
    1.05
     when
    1.05
     change
    1.04
     to
    1.02
    以前的
    1.01
     we
    1.01
     plans
    0.99
    Activations Density 0.002%

    No Known Activations