© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112311
    Prev
    Next
    INDEX
    Explanations

    android resource ids

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

    underscores in Android code identifiers, particularly in layout and resource names.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     deberán
    -1.57
     THOSE
    -1.44
    ccato
    -1.41
     miatt
    -1.41
    owych
    -1.40
     altamente
    -1.34
     cubiertos
    -1.32
    一时间
    -1.30
    escence
    -1.27
     SHOULD
    -1.27
    POSITIVE LOGITS
     of
    1.78
    噐
    1.59
     storie
    1.52
     for
    1.51
    liwości
    1.45
    餽
    1.45
     at
    1.43
    呖
    1.41
     colab
    1.38
     ricordare
    1.37
    Activations Density 0.006%

    No Known Activations