© 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. 72930
    Prev
    Next
    INDEX
    Explanations

    entity names and associated categories

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

    specific terms followed by related 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
     ਸਮ
    0.43
     నొప్పి
    0.43
     hypothalamus
    0.41
    ിയാണ്
    0.40
    みる
    0.38
     hippocampus
    0.38
    এ
    0.37
     مع
    0.37
     راستہ
    0.37
     کلی
    0.37
    POSITIVE LOGITS
     aficionados
    0.55
    所在的
    0.46
     admirer
    0.44
     supporters
    0.43
    专门
    0.43
     специализирован
    0.42
    কারী
    0.42
     admirers
    0.42
    al
    0.42
    id
    0.42
    Activations Density 0.393%

    No Known Activations