© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 219290
    Prev
    Next
    INDEX
    Explanations

    and or

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

    fast, easy, rapidly

    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
     Gases
    0.44
     பகுதியில்
    0.44
     amines
    0.43
    Trusted
    0.43
     HttpException
    0.42
     আশঙ্কা
    0.42
    		
    0.42
    ,
    0.42
     vulnerabilities
    0.41
    住在
    0.40
    POSITIVE LOGITS
    銛
    0.47
    ாடு
    0.46
    多様
    0.46
    ੀ
    0.45
     lij
    0.45
    いない
    0.45
    鳥
    0.45
     fulfills
    0.45
     رکھنا
    0.44
     veel
    0.44
    Activations Density 0.000%

    No Known Activations