© 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. 30673
    Prev
    Next
    INDEX
    Explanations

    web addresses and links

    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
    τω
    -0.90
    Forgery
    -0.89
     اذا
    -0.86
    γο
    -0.82
    Relo
    -0.81
     irány
    -0.80
     žele
    -0.79
    IRM
    -0.78
    capace
    -0.77
     conceptual
    -0.76
    POSITIVE LOGITS
    esac
    0.92
     دسترسی
    0.80
    hyperref
    0.76
    Noon
    0.75
    zot
    0.68
     defends
    0.68
    arXiv
    0.68
     Acesso
    0.67
    Wallace
    0.67
    Ning
    0.67
    Activations Density 0.000%

    No Known Activations