© 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-262K
    7. 25425
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

    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_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
     providence
    0.40
     Kn
    0.38
     Rug
    0.37
    盛り
    0.37
     Nad
    0.37
     إ
    0.36
     rugged
    0.35
    盛
    0.35
    性に
    0.35
    🔋
    0.35
    POSITIVE LOGITS
    Connector
    0.49
    navigationLinks
    0.48
    LinkLabel
    0.44
     Connector
    0.40
     connects
    0.40
     conecta
    0.39
    lucene
    0.38
     Indicator
    0.38
     पाण्डे
    0.38
    izia
    0.38
    Activations Density 0.010%

    No Known Activations