© 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-65K
    7. 4856
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or contrast

    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_65k_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
     financial
    0.47
     required
    0.47
     needed
    0.44
    і
    0.44
     charges
    0.44
     transaction
    0.43
     abuses
    0.43
     emotions
    0.42
    our
    0.42
    方式
    0.41
    POSITIVE LOGITS
    如果你
    0.57
    如果是
    0.50
    墘
    0.48
     अगर
    0.47
    अगर
    0.47
     окра
    0.47
    如果我们
    0.47
    记载
    0.46
    譬
    0.45
     Reasoning
    0.45
    Activations Density 0.002%

    No Known Activations