© 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. 22-GEMMASCOPE-RES-131K
    7. 64646
    Prev
    Next
    INDEX
    Explanations

    finally, lastly

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron doesn’t reliably activate on any tokens (i.e. it isn’t detecting any specific pattern in these examples).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    んでしょう
    -1.32
     and
    -1.28
    durante
    -1.26
    觊
    -1.23
     unglaub
    -1.16
     repuesto
    -1.13
    seguida
    -1.13
    のですか
    -1.12
     antaranya
    -1.12
    cómo
    -1.12
    POSITIVE LOGITS
    Lastly
    1.57
     it
    1.55
    なので
    1.51
     is
    1.36
     finally
    1.30
    ですが
    1.27
     TÉCNICA
    1.23
     Finally
    1.22
    ぜひ
    1.20
    Finally
    1.20
    Activations Density 0.077%

    No Known Activations