© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 109150
    Prev
    Next
    INDEX
    Explanations

    cliff and associated phrases

    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_40_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
     खो
    0.45
     Cross
    0.38
    को
    0.38
     ти
    0.37
    τι
    0.37
    <(
    0.37
     crossed
    0.36
     bothered
    0.36
    チェーン
    0.36
    姜
    0.36
    POSITIVE LOGITS
    hanger
    0.76
    Cliff
    0.70
     cliff
    0.68
     Cliff
    0.64
     cliffs
    0.57
     dwellings
    0.57
    崖
    0.57
     face
    0.53
     hanger
    0.53
    cliff
    0.52
    Activations Density 0.003%

    No Known Activations