© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35410
    Prev
    Next
    INDEX
    Explanations

    technical identifiers

    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
     isolamento
    -1.48
     alça
    -1.45
     manquer
    -1.42
    grats
    -1.41
     velha
    -1.40
     ſtate
    -1.38
    amplific
    -1.36
    ほとん
    -1.35
    pochette
    -1.35
    embro
    -1.34
    POSITIVE LOGITS
     its
    1.58
    PO
    1.44
    x
    1.44
    m
    1.44
    RE
    1.43
    r
    1.37
    CO
    1.36
     $
    1.36
    f
    1.36
    om
    1.35
    Activations Density 0.173%

    No Known Activations