© 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. 4615
    Prev
    Next
    INDEX
    Explanations

    understanding and getting information

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

    religious terms and pronouns

    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
     instructing
    0.37
     Annotation
    0.36
     instruction
    0.35
     indicating
    0.35
     instructions
    0.34
    ych
    0.33
    ကြ
    0.33
    ঃ
    0.33
     Parser
    0.33
    )<
    0.33
    POSITIVE LOGITS
    Nor
    0.37
    ပဲ
    0.37
    Veja
    0.36
     نعمت
    0.36
    設備の
    0.35
     anzi
    0.34
     подряд
    0.34
     sahip
    0.34
     Вообще
    0.34
     blanca
    0.33
    Activations Density 0.071%

    No Known Activations