© 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. 53-GEMMASCOPE-2-RES-262K
    7. 82006
    Prev
    Next
    INDEX
    Explanations

    Mathematical term prefixes

    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_53_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
     taas
    0.52
    obj
    0.48
     */
    0.44
    idt
    0.43
    arctan
    0.41
    etat
    0.41
    higher
    0.41
     sapply
    0.40
     hoger
    0.40
     trochę
    0.40
    POSITIVE LOGITS
     $_{\
    0.47
    Vincent
    0.42
    ––
    0.42
     $_{
    0.41
    ハリ
    0.40
     заболевания
    0.39
     COMMUNITY
    0.38
    Cone
    0.38
    ﴾
    0.38
    <sub>
    0.38
    Activations Density 0.002%

    No Known Activations