© 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. 113364
    Prev
    Next
    INDEX
    Explanations

    wrapper objects look

    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
     mentre
    0.54
     nuove
    0.50
     efficacement
    0.47
     passionately
    0.47
    ȋ
    0.46
     ರೀತಿ
    0.46
     হেঁটে
    0.45
     médiocrement
    0.45
    するとき
    0.45
     և
    0.44
    POSITIVE LOGITS
     weight
    0.47
    特殊
    0.46
     looked
    0.44
     packets
    0.43
    者
    0.42
     some
    0.42
     Cookie
    0.42
     turn
    0.41
     Packet
    0.41
     shape
    0.40
    Activations Density 0.004%

    No Known Activations