© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191279
    Prev
    Next
    INDEX
    Explanations

    quantifier + descriptor

    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_40_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
     сбор
    0.42
    bigvee
    0.40
     nominated
    0.38
    Ja
    0.38
     anyone
    0.36
     ducha
    0.36
     संग्रहण
    0.36
     後
    0.35
    !")
    0.35
     jau
    0.35
    POSITIVE LOGITS
     parallèles
    0.44
     parallèle
    0.43
     দ্রুত
    0.41
     অস
    0.40
     (_,
    0.40
     கவனம்
    0.40
    ینا
    0.39
    冭
    0.39
     علا
    0.38
    basically
    0.38
    Activations Density 0.000%

    No Known Activations