© 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. 780
    Prev
    Next
    INDEX
    Explanations

    promoting sustainability and energy

    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
     verbinden
    0.32
     motoc
    0.32
    Khokhlov
    0.31
     bittern
    0.31
    Scorch
    0.31
    ڡ
    0.30
     réalise
    0.30
    ൮
    0.30
    Pole
    0.30
     realizó
    0.30
    POSITIVE LOGITS
     don
    0.29
      
    0.26
     fal
    0.25
     各
    0.25
    la
    0.25
     "
    0.24
    ス
    0.24
     食品
    0.23
     tac
    0.23
    its
    0.23
    Activations Density 0.000%

    No Known Activations