© 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. 16-GEMMASCOPE-2-RES-262K
    7. 17782
    Prev
    Next
    INDEX
    Explanations

    names and triggers

    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_16_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
    י
    1.41
     are
    1.30
    いた
    1.26
    j
    1.26
    ری
    1.23
    ના
    1.23
    i
    1.22
    ও
    1.22
     in
    1.21
    は
    1.16
    POSITIVE LOGITS
    л
    1.34
    ashed
    1.26
    rát
    1.21
    ت
    1.18
    تس
    1.17
    isches
    1.14
    ákat
    1.14
    ె
    1.13
    لما
    1.10
    áme
    1.09
    Activations Density 0.011%

    No Known Activations