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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52854
    Prev
    Next
    INDEX
    Explanations

    beyond and related context

    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_262k_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
    та
    0.53
    пусти
    0.44
    л
    0.43
     Д
    0.41
    웁
    0.40
     нашу
    0.40
    ל
    0.40
    на
    0.40
     наси
    0.40
    ле
    0.39
    POSITIVE LOGITS
     stér
    0.50
    nahme
    0.43
     préoccup
    0.42
    keyList
    0.42
     rulemaking
    0.41
    ေါ်
    0.41
     uncertainty
    0.40
     féd
    0.40
    fieldContext
    0.40
     exhort
    0.39
    Activations Density 0.002%

    No Known Activations