© 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. 84151
    Prev
    Next
    INDEX
    Explanations

    property substantive

    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
     concomitant
    0.38
     destroys
    0.38
     wastage
    0.38
    __[
    0.36
     accelerate
    0.36
    γγ
    0.36
    だけの
    0.36
    ạch
    0.35
     तत्कालीन
    0.35
     societies
    0.35
    POSITIVE LOGITS
    煐
    0.42
    ANDO
    0.39
     jestem
    0.38
     Saúde
    0.38
    पान
    0.38
     размер
    0.37
     кух
    0.37
     Attitude
    0.37
     ጣ
    0.36
     ನಾನು
    0.35
    Activations Density 0.000%

    No Known Activations