© 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-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1831
    Prev
    Next
    INDEX
    Explanations

    control, available, APIs, cache

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    翠
    0.96
    sin
    0.89
     acheter
    0.87
    educ
    0.86
    ext
    0.85
    孕
    0.84
    έλ
    0.84
     storie
    0.81
     concave
    0.81
    shapes
    0.81
    POSITIVE LOGITS
     সেক্ষেত্রে
    1.16
     fn
    1.11
     fB
    1.11
     Levante
    1.07
    >∕
    1.05
    लंघन
    1.02
    ffes
    0.99
    pytorch
    0.99
     PRA
    0.99
    RestClient
    0.99
    Activations Density 0.000%

    No Known Activations