© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 16873
    Prev
    Next
    INDEX
    Explanations

    labels followed by numbers or prices

    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
    致力于
    0.46
     sogenannten
    0.44
    专注于
    0.43
    醅
    0.43
    应用于
    0.43
    SourceRequest
    0.42
    说着
    0.42
     기본적인
    0.41
    രിക്കുന്ന
    0.40
     пользователь
    0.40
    POSITIVE LOGITS
    8
    1.00
    7
    0.96
    6
    0.96
    5
    0.91
    9
    0.84
    4
    0.81
    3
    0.78
    1
    0.78
     
    0.76
     $
    0.71
    Activations Density 0.095%

    No Known Activations