© 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. 34-GEMMASCOPE-RES-131K
    7. 103481
    Prev
    Next
    INDEX
    Explanations

    except

    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
    layoutControl
    -0.78
    pads
    -0.76
     short
    -0.69
    TCM
    -0.69
    atia
    -0.67
     early
    -0.67
    BIA
    -0.66
    ਿੰ
    -0.66
     ninguna
    -0.65
     dejan
    -0.65
    POSITIVE LOGITS
    ansons
    0.84
    ДУ
    0.70
     آم
    0.69
     konstru
    0.68
     mammary
    0.68
    сми
    0.67
    ='"
    0.66
    tableWidget
    0.65
    Blanco
    0.65
    Exc
    0.64
    Activations Density 0.059%

    No Known Activations