© 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. 129511
    Prev
    Next
    INDEX
    Explanations

    conclusion phrase final words

    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
     therefore
    -0.99
    のですか
    -0.94
     sya
    -0.93
     operações
    -0.91
     saus
    -0.91
     officio
    -0.90
     ursprünglich
    -0.90
    に行って
    -0.90
    deno
    -0.89
     ENERG
    -0.89
    POSITIVE LOGITS
     lastly
    2.08
    Lastly
    1.95
     Lastly
    1.92
    Finally
    1.84
     Finally
    1.66
     finally
    1.59
    これも
    1.54
     enfin
    1.51
    finally
    1.46
    こちらも
    1.23
    Activations Density 0.016%

    No Known Activations