© 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. 27947
    Prev
    Next
    INDEX
    Explanations

    period followed by "These"

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

    tense and relax

    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
    峤
    0.50
     الوسط
    0.49
    ኘት
    0.47
     Plattform
    0.47
     PHY
    0.47
     Noon
    0.46
     Abo
    0.46
     Tien
    0.46
     Photograph
    0.45
    ቂ
    0.45
    POSITIVE LOGITS
     شیر
    0.48
    affected
    0.45
    علم
    0.45
    )].
    0.43
     знали
    0.43
     मिठ
    0.41
     知
    0.40
     знал
    0.40
    ந்திரன்
    0.39
    ана
    0.39
    Activations Density 0.000%

    No Known Activations