© 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. 104237
    Prev
    Next
    INDEX
    Explanations

    fish and birds

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

    names of fish species or fish-related terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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>
    -1.84
     well
    -1.74
     exigencias
    -1.70
     dokład
    -1.62
     行き
    -1.57
    ęcie
    -1.55
     девочка
    -1.55
     confident
    -1.53
     casado
    -1.52
    itigen
    -1.52
    POSITIVE LOGITS
    痕
    1.57
    ekš
    1.43
     kehamilan
    1.40
     Atención
    1.39
     {
    1.39
    \"
    1.37
    нав
    1.36
    ⊺
    1.36
    糠
    1.35
     Anſ
    1.33
    Activations Density 0.016%

    No Known Activations