© 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. 10-GEMMASCOPE-RES-131K
    7. 9849
    Prev
    Next
    INDEX
    Explanations

    used or applied in context

    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_10/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
    </strong>
    -1.80
    stander
    -1.51
     but
    -1.49
    ???:
    -1.41
    </b>
    -1.38
    </sup>
    -1.32
     said
    -1.32
    z
    -1.30
    de
    -1.29
    !(:
    -1.29
    POSITIVE LOGITS
     zle
    1.40
    kimi
    1.28
     quelquefois
    1.25
    Weiß
    1.25
    aş
    1.24
    não
    1.24
    They
    1.23
     arasındaki
    1.20
    cami
    1.20
    Honestly
    1.20
    Activations Density 0.060%

    No Known Activations