© 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. 42051
    Prev
    Next
    INDEX
    Explanations

    Adjust layout

    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
    avacanam
    0.50
    ات
    0.47
     அல்லது
    0.47
    ة
    0.47
    监
    0.42
     amerikan
    0.42
    ⌬
    0.42
    ام
    0.41
    舶
    0.41
    append
    0.41
    POSITIVE LOGITS
     श्रीदेवी
    0.47
     hoodie
    0.44
     shameful
    0.44
     genocide
    0.44
     bidirectional
    0.44
     Cinderella
    0.43
     subnet
    0.42
     ReLU
    0.42
     afternoons
    0.42
     sedentary
    0.42
    Activations Density 0.001%

    No Known Activations