© 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. 170242
    Prev
    Next
    INDEX
    Explanations

    use is subject to terms and consequences

    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
     chemically
    0.45
    祯
    0.43
    当我们
    0.41
    Fact
    0.39
     fully
    0.38
     electronically
    0.38
     as
    0.38
                         
    0.37
     نف
    0.37
    葭
    0.37
    POSITIVE LOGITS
    ಿಣ
    0.46
     Erkrank
    0.44
    崛起
    0.44
     treacherous
    0.43
     restrictions
    0.41
     forbidden
    0.41
     दंग
    0.41
     psychopath
    0.40
    超时
    0.40
     affront
    0.39
    Activations Density 0.007%

    No Known Activations