© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45222
    Prev
    Next
    INDEX
    Explanations

    students discuss, analyze, explain

    np_acts-logits-general · gemini-2.5-flash-lite

    political groups or roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     computer
    0.45
    კო
    0.45
     padding
    0.44
     글
    0.43
     reality
    0.42
    ADI
    0.41
     prototype
    0.40
    裵
    0.40
     fat
    0.40
    ፔ
    0.40
    POSITIVE LOGITS
    gå
    0.48
     必ず
    0.46
    mong
    0.44
    amalla
    0.44
     کرا
    0.44
    မဲ့
    0.44
     telah
    0.44
    äm
    0.43
     উদ্বাস্তু
    0.43
    nyt
    0.42
    Activations Density 0.000%

    No Known Activations