© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212754
    Prev
    Next
    INDEX
    Explanations

    foreign numbers or words

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

    visible light spectrum

    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_31_width_262k_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
    ⓪
    0.51
    ↵
    0.49
    ownt
    0.45
    ardia
    0.44
    iak
    0.43
     Accountability
    0.43
    ኻ
    0.41
    𝓊
    0.40
    inned
    0.40
    学会
    0.40
    POSITIVE LOGITS
     trei
    0.48
     jei
    0.47
     testen
    0.46
    ස්
    0.45
     zehn
    0.45
     drei
    0.44
     polych
    0.44
     emis
    0.44
     tři
    0.44
    沘
    0.43
    Activations Density 0.000%

    No Known Activations