© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 66615
    Prev
    Next
    INDEX
    Explanations

    person or event

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

    AI assistant identification

    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
    은
    0.49
    пети
    0.44
     provoca
    0.44
    彤
    0.44
     provoke
    0.43
    прово
    0.43
    는
    0.43
    엮
    0.42
     scegliere
    0.41
     suelen
    0.41
    POSITIVE LOGITS
    ئا
    0.51
    injury
    0.47
    ijnlijk
    0.47
    粔
    0.46
    damage
    0.45
     дому
    0.45
     अंग्रेज
    0.45
     Suns
    0.45
     elke
    0.44
    absence
    0.44
    Activations Density 0.002%

    No Known Activations