© 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. 48327
    Prev
    Next
    INDEX
    Explanations

    affirmative or negative responses

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

    changed to

    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
     රා
    0.43
    するもの
    0.43
    吕
    0.42
     શિક્ષણ
    0.40
     schemas
    0.40
     துணை
    0.39
     تاز
    0.39
    峦
    0.39
    தர
    0.38
    مراجع
    0.38
    POSITIVE LOGITS
     Wouldn
    0.53
    this
    0.52
     this
    0.52
    yes
    0.51
     questo
    0.50
     nope
    0.50
     이건
    0.50
    This
    0.48
     This
    0.47
    앗
    0.47
    Activations Density 0.017%

    No Known Activations