© 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. 45674
    Prev
    Next
    INDEX
    Explanations

    factory, orientation, fullness, limited scalability, curiosity hooks

    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
    ה
    0.47
    이나
    0.40
     tornou
    0.40
     anon
    0.40
    치
    0.40
     DEPENDENCIA
    0.38
    እ
    0.38
     、
    0.38
    就算
    0.38
     chute
    0.38
    POSITIVE LOGITS
     intervening
    0.44
     essays
    0.43
     മേഖല
    0.41
     takeaways
    0.41
     Кри
    0.40
     kans
    0.40
    ｝
    0.40
     ranges
    0.39
    كري
    0.39
    মাকে
    0.39
    Activations Density 0.001%

    No Known Activations