© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4715
    Prev
    Next
    INDEX
    Explanations

    identifying types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    False
    1.35
    鹼
    1.31
     TRUE
    1.28
     yaitu
    1.24
     sehari
    1.16
    dear
    1.15
     users
    1.13
     Students
    1.12
    FALSE
    1.12
     True
    1.11
    POSITIVE LOGITS
    isci
    1.93
    agerie
    1.89
    影响力
    1.88
    佘
    1.84
     plumage
    1.83
    hbs
    1.80
     Retour
    1.78
    repr
    1.77
     briefings
    1.70
    Kaynakça
    1.69
    Activations Density 0.010%

    No Known Activations