© 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. 1759
    Prev
    Next
    INDEX
    Explanations

    actions and states of being

    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
     також
    0.47
     גם
    0.44
     них
    0.43
     მათ
    0.42
     juga
    0.42
     myös
    0.42
     também
    0.42
    }$.
    0.41
     också
    0.41
     ebenfalls
    0.41
    POSITIVE LOGITS
     inilah
    0.31
     European
    0.31
     olyan
    0.31
     phosphorylated
    0.30
     Australian
    0.30
    、
    0.30
    oretically
    0.29
     কারণেই
    0.29
     a
    0.29
    なのですが
    0.29
    Activations Density 0.518%

    No Known Activations