© 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. 111307
    Prev
    Next
    INDEX
    Explanations

    BMW vehicles and company information

    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
    благо
    0.44
     Здравствуйте
    0.42
    㠱
    0.42
     Bordeaux
    0.41
    觕
    0.41
     Calvary
    0.40
    傷害
    0.40
     referral
    0.39
     perfecta
    0.39
     Parad
    0.39
    POSITIVE LOGITS
    BMW
    0.42
    Woh
    0.38
     inscr
    0.37
    [::-
    0.36
     BMW
    0.36
    scrollbar
    0.36
    orns
    0.35
    claves
    0.35
    目光
    0.34
    SAV
    0.34
    Activations Density 0.006%

    No Known Activations