© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3995
    Prev
    Next
    INDEX
    Explanations

    been after s

    np_acts-logits-general · gemini-2.5-flash-lite

    's got

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indeed
    0.59
    indeed
    0.54
     Indeed
    0.53
    Indeed
    0.50
     infatti
    0.45
    せずに
    0.45
    ">,</
    0.45
     但是
    0.45
    ofil
    0.45
     或者
    0.44
    POSITIVE LOGITS
     been
    2.25
    been
    2.13
    Been
    1.95
     Been
    1.88
     BEEN
    1.87
     got
    1.59
     gotta
    1.43
     ollut
    1.40
    got
    1.33
     vært
    1.27
    Activations Density 0.215%

    No Known Activations