© 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. 123456
    Prev
    Next
    INDEX
    Explanations

    a householdnitric aciddrafted anyonemobilization and

    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
    ކ
    0.46
     acteurs
    0.46
     satirical
    0.46
    󰡔
    0.45
     tikai
    0.43
     `:`
    0.43
     auteur
    0.43
    ِينَ
    0.43
    ይ
    0.43
     perpetrators
    0.43
    POSITIVE LOGITS
     বেঁচে
    0.44
    izzi
    0.40
     conjugated
    0.39
    सेवी
    0.39
     solubilities
    0.38
     рассчиты
    0.38
    iewicz
    0.38
    assanam
    0.38
     Cit
    0.37
     Unidas
    0.37
    Activations Density 0.005%

    No Known Activations