© 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. 10-GEMMASCOPE-RES-131K
    7. 8042
    Prev
    Next
    INDEX
    Explanations

    Australasian, Northeastern, xhtml, Dixie

    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_10/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
    螃
    -2.63
    湏
    -2.53
    Ꮉ
    -2.50
    銠
    -2.44
    ми
    -2.39
    ffled
    -2.36
    ⇹
    -2.36
    眛
    -2.34
    
    -2.33
    咴
    -2.28
    POSITIVE LOGITS
    9
    2.55
    While
    2.47
    With
    2.45
    isation
    2.42
    When
    2.39
     definitivo
    2.39
    Using
    2.36
    During
    2.30
     並
    2.25
    After
    2.23
    Activations Density 0.004%

    No Known Activations