© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 1633
    Prev
    Next
    INDEX
    Explanations

    wildlife herds and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     इश्
    0.54
    Trailing
    0.46
    撸
    0.46
     lézard
    0.46
    NodeType
    0.44
    鹦
    0.43
    acat
    0.42
    萜
    0.42
    மையில்
    0.42
     नारियल
    0.41
    POSITIVE LOGITS
     herds
    0.73
     herd
    0.67
     wilde
    0.54
     flocks
    0.54
     群
    0.54
     grandes
    0.52
     nomads
    0.51
     migrate
    0.49
     большие
    0.49
     hordes
    0.48
    Activations Density 0.029%

    No Known Activations