© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53005
    Prev
    Next
    INDEX
    Explanations

    lakes and ponds

    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_65k_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
    崖
    0.42
    দ্য
    0.41
    Coastal
    0.41
     Branco
    0.40
    ారా
    0.40
     উপকূল
    0.40
     coastal
    0.39
    চট্টগ্রাম
    0.39
    telefone
    0.39
    آم
    0.39
    POSITIVE LOGITS
     lake
    1.33
    湖
    1.17
    Lake
    1.14
     Lake
    1.11
     lakeside
    1.10
     lakes
    1.08
     LAKE
    1.07
     झील
    1.05
     озеро
    1.01
    lake
    0.92
    Activations Density 0.081%

    No Known Activations