© 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. 34-GEMMASCOPE-RES-131K
    7. 49485
    Prev
    Next
    INDEX
    Explanations

    moving on or onto

    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
     jól
    -0.85
    のではないか
    -0.83
    ことがある
    -0.82
    typer
    -0.80
     deviennent
    -0.80
     celu
    -0.79
    近づ
    -0.79
    ކ
    -0.78
     colgantes
    -0.78
     devaient
    -0.77
    POSITIVE LOGITS
     onto
    5.34
    onto
    3.48
     Ont
    3.25
    Ont
    3.19
     onwards
    2.64
     onward
    2.50
    ONTO
    2.16
     on
    1.77
     unto
    1.74
    ontological
    1.73
    Activations Density 0.043%

    No Known Activations