© 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-16K
    7. 13522
    Prev
    Next
    INDEX
    Explanations

    ending quotes followed by attribution

    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_16k_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
     phrasing
    0.44
    Nathan
    0.41
     विद्व
    0.39
    渽
    0.37
    น้ำ
    0.36
    ">,</
    0.36
     Nathan
    0.36
    MatContext
    0.35
     féri
    0.35
    工作人员
    0.34
    POSITIVE LOGITS
    en
    0.48
    is
    0.46
    an
    0.45
    un
    0.44
    精心
    0.44
    ᱗
    0.42
    ip
    0.42
    ipu
    0.42
     _{(
    0.41
    us
    0.41
    Activations Density 0.007%

    No Known Activations