© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83992
    Prev
    Next
    INDEX
    Explanations

    hermit, hermitage, herminic, hermiticity

    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
    ઁ
    -3.11
     tênis
    -2.58
     nhưng
    -2.56
     acidente
    -2.44
    謦
    -2.44
    CurtirCurtir
    -2.44
    ൎ
    -2.44
    ᷆
    -2.44
     dinoss
    -2.36
    ឵
    -2.36
    POSITIVE LOGITS
    me
    2.69
    ”,
    2.63
    ”.
    2.63
    <i>
    2.47
    ),
    2.45
    ↵
    2.41
     –
    2.39
    2.33
    ’
    2.28
     bewegt
    2.23
    Activations Density 0.008%

    No Known Activations