© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66739
    Prev
    Next
    INDEX
    Explanations

    starts of phrases or sentences

    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
    Oktober
    -1.09
    另一個
    -1.05
    تاريخ
    -1.02
     "
    -1.02
    来年
    -1.02
    Länge
    -1.00
    Rozmiar
    -0.99
    ㄡ
    -0.99
    Polecam
    -0.99
     zobaczyć
    -0.99
    POSITIVE LOGITS
    point
    1.14
    á
    1.11
    be
    1.05
    z
    1.05
    er
    1.05
    al
    1.02
    𝙥
    1.02
    on
    1.01
    an
    1.00
    j
    1.00
    Activations Density 0.000%

    No Known Activations