© 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. 584
    Prev
    Next
    INDEX
    Explanations

    connecting words

    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
     negativity
    0.24
    -{\
    0.24
    sbParams
    0.24
    GTBase
    0.24
     বিশ্লেষণ
    0.23
    merksam
    0.23
     hydroph
    0.23
    beitung
    0.23
     gneiss
    0.23
     vinaig
    0.23
    POSITIVE LOGITS
    а
    0.39
     or
    0.38
    на
    0.37
    и
    0.37
     và
    0.36
    在
    0.36
    and
    0.36
     или
    0.35
     ಮತ್ತು
    0.35
    और
    0.35
    Activations Density 2.553%

    No Known Activations