© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1609
    Prev
    Next
    INDEX
    Explanations

    future ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     V
    0.86
    '
    0.85
     Y
    0.84
     Re
    0.82
     Se
    0.82
    pl
    0.80
     T
    0.80
     D
    0.80
     v
    0.79
     Mc
    0.79
    POSITIVE LOGITS
     nasc
    1.46
     onRequest
    1.42
     stumpage
    1.41
     sukham
    1.41
    <unused1728>
    1.40
     теркә
    1.39
     arugula
    1.39
     serializers
    1.38
    السلام
    1.38
    <unused1691>
    1.36
    Activations Density 1.040%

    No Known Activations