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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12211
    Prev
    Next
    INDEX
    Explanations

    protected natural areas

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

    descriptions of natural protected areas like national parks, nature preserves, and sites of special scientific interest.

    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_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
    饷
    -1.49
    作战
    -1.41
     kiezen
    -1.37
     modelleri
    -1.36
     médec
    -1.34
    Detalhes
    -1.34
     tevreden
    -1.31
    İş
    -1.31
     klaar
    -1.30
     voordelen
    -1.30
    POSITIVE LOGITS
    魔女
    1.39
    อร่อย
    1.35
     biodiversity
    1.29
     preserved
    1.27
     undisturbed
    1.26
     संर
    1.20
    Ў
    1.18
     algorit
    1.16
     kuid
    1.15
    ⵜ
    1.14
    Activations Density 0.079%

    No Known Activations