© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 490
    Prev
    Next
    INDEX
    Explanations

    river floodplain and mountains

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

    stream, coastline, river, forest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    де
    0.45
    ди
    0.45
    тор
    0.43
    ém
    0.42
    он
    0.42
     были
    0.42
     фонда
    0.41
    м
    0.40
    1
    0.39
    ция
    0.39
    POSITIVE LOGITS
     River
    0.55
     I
    0.50
     you
    0.49
    IN
    0.48
    "
    0.48
     Forest
    0.46
     river
    0.46
    Forest
    0.46
    }
    0.45
     Wild
    0.43
    Activations Density 1.131%

    No Known Activations