© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4663
    Prev
    Next
    INDEX
    Explanations

    handling `return None`

    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_15_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
     vaan
    1.01
     grond
    0.94
    jeg
    0.84
    셩
    0.84
    లి
    0.82
     consolid
    0.80
     míst
    0.78
    pler
    0.76
     Crystallogr
    0.75
    澈
    0.73
    POSITIVE LOGITS
    MathClass
    1.63
    egna
    1.55
     hyn
    1.53
    odds
    1.53
    pués
    1.53
     uranyl
    1.52
    inni
    1.50
    Duplicates
    1.50
    EDES
    1.49
    ᵍ
    1.49
    Activations Density 0.040%

    No Known Activations