© 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. 7609
    Prev
    Next
    INDEX
    Explanations

    relationship, connections, links

    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
     bertujuan
    0.44
     声
    0.42
    istice
    0.41
    萫
    0.40
    菽
    0.40
    环保
    0.39
     TEA
    0.39
    乐
    0.39
    ǎn
    0.38
    <unused1112>
    0.38
    POSITIVE LOGITS
     existing
    0.48
     previous
    0.48
     other
    0.46
     kindred
    0.45
     '../
    0.44
     relatable
    0.44
     connect
    0.44
     afflict
    0.43
     nearby
    0.43
     connections
    0.42
    Activations Density 0.000%

    No Known Activations