© 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. 173014
    Prev
    Next
    INDEX
    Explanations

    apostle Peter or US Open

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

    Economic nuances and willingness

    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
    ༌
    0.51
     pformat
    0.47
    ]]$
    0.46
     세율
    0.46
    哺
    0.44
     sostenibilidad
    0.44
    ノン
    0.43
     elaborar
    0.43
     razones
    0.43
     infrastructural
    0.43
    POSITIVE LOGITS
    line
    0.63
    lu
    0.60
    ig
    0.58
    lin
    0.57
    lasse
    0.55
    lv
    0.52
    lü
    0.51
    l
    0.51
    las
    0.50
    ingham
    0.50
    Activations Density 0.001%

    No Known Activations