Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 19201
    Prev
    Next
    INDEX
    Explanations

    abundance and scarcity

    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
     erfol
    0.45
     itself
    0.41
    였습니다
    0.39
    ბ
    0.39
     besitzt
    0.38
    含有
    0.37
     eigene
    0.37
     possesses
    0.36
    शिला
    0.36
     contains
    0.35
    POSITIVE LOGITS
     plentiful
    0.64
     galore
    0.58
     abound
    0.56
     everywhere
    0.45
     scarce
    0.45
    เยอะ
    0.44
    ାଇ
    0.43
    KING
    0.43
    ᆹ
    0.43
     abond
    0.41
    Activations Density 0.021%

    No Known Activations