© 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. 135928
    Prev
    Next
    INDEX
    Explanations

    beautiful city

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

    verbs and nouns

    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
    ঁর
    0.46
    </h4>
    0.46
    Slate
    0.45
    edDevice
    0.45
    MFC
    0.44
     sols
    0.44
    Zombie
    0.44
    Gang
    0.43
    scientists
    0.43
    science
    0.43
    POSITIVE LOGITS
    ة
    0.57
     Canadá
    0.51
     Этот
    0.48
    Этот
    0.48
     capítulo
    0.47
     opções
    0.47
     этот
    0.44
    ુ
    0.44
     Ángel
    0.43
     be
    0.42
    Activations Density 0.001%

    No Known Activations