© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26004
    Prev
    Next
    INDEX
    Explanations

    organization and competition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Б
    0.55
    К
    0.54
    дом
    0.51
    \
    0.49
    Т
    0.49
    Х
    0.49
    М
    0.49
    دهای
    0.48
    ᔾ
    0.48
    కు
    0.48
    POSITIVE LOGITS
     escolar
    0.38
     हवाई
    0.38
     colet
    0.37
    organizzazione
    0.37
    organization
    0.37
     organización
    0.37
     takže
    0.36
     marketing
    0.36
    ーター
    0.36
     playful
    0.35
    Activations Density 0.001%

    No Known Activations