© 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. 93302
    Prev
    Next
    INDEX
    Explanations

    programming and disclaimers

    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
     víctima
    -0.79
    aimer
    -0.76
     uzyskać
    -0.75
    Pubs
    -0.75
    rodek
    -0.75
    Aims
    -0.74
     vanished
    -0.73
     instancia
    -0.72
     eût
    -0.71
    ganos
    -0.71
    POSITIVE LOGITS
    andExpect
    1.13
    TextColor
    0.76
     αὐτ
    0.76
     ourselves
    0.73
    ODO
    0.73
     enriquec
    0.73
    Mailbox
    0.72
     Pretty
    0.71
    getContentPane
    0.69
    zió
    0.69
    Activations Density 0.001%

    No Known Activations