© 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. 47385
    Prev
    Next
    INDEX
    Explanations

    their place

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

    special characters and conversational structure

    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
    ಡಿಯ
    0.49
     foci
    0.49
    訂
    0.46
    瞭
    0.45
     dishonesty
    0.45
     resampling
    0.45
     hooking
    0.44
    満
    0.44
     convincing
    0.43
     stakeholder
    0.43
    POSITIVE LOGITS
     ৃ
    0.52
     ويك
    0.51
     וי
    0.47
     básicos
    0.47
     וא
    0.46
     немно
    0.46
     Vorstellung
    0.45
     وليس
    0.45
     মৌলিক
    0.45
     אשר
    0.45
    Activations Density 0.000%

    No Known Activations