© 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. 40-GEMMASCOPE-2-RES-262K
    7. 137
    Prev
    Next
    INDEX
    Explanations

    algorithms and proofs

    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
    咬
    0.47
     devotional
    0.45
     sculptural
    0.44
     वास
    0.44
    śli
    0.44
    aithe
    0.43
     sebum
    0.43
     vocals
    0.42
     piena
    0.42
    裹
    0.42
    POSITIVE LOGITS
     Algorithms
    0.86
     algorithms
    0.84
     Algorithm
    0.81
    Algorithms
    0.80
    Algorithm
    0.77
     algorithm
    0.75
     algorithmic
    0.73
    algorithms
    0.73
     algorit
    0.72
     алгорит
    0.71
    Activations Density 0.034%

    No Known Activations