© 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. 397
    Prev
    Next
    INDEX
    Explanations

    compete in

    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
     bowlers
    1.48
     verdana
    1.42
    ortium
    1.36
    (!$
    1.34
    ítě
    1.30
     piglets
    1.25
     Tew
    1.24
    állítás
    1.23
     $=$
    1.20
     prawns
    1.20
    POSITIVE LOGITS
    7
    1.87
    0
    1.70
    8
    1.68
    3
    1.65
    start
    1.52
    1
    1.51
     wellness
    1.50
    5
    1.47
    color
    1.44
    6
    1.44
    Activations Density 0.057%

    No Known Activations