© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6426
    Prev
    Next
    INDEX
    Explanations

    possibility, process, or state

    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
    €“
    2.02
    €”
    1.89
    d
    1.88
     of
    1.87
    id
    1.83
    –
    1.81
    -
    1.80
    of
    1.79
    eta
    1.79
     précisément
    1.75
    POSITIVE LOGITS
     것도
    1.86
    것도
    1.69
     것처럼
    1.63
     것은
    1.62
    時候
    1.59
     것을
    1.58
    时候
    1.55
    際に
    1.50
     것에
    1.48
    것
    1.45
    Activations Density 0.008%

    No Known Activations