© 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. 194125
    Prev
    Next
    INDEX
    Explanations

    blooms

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

    pumping lemma

    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
    領域
    0.52
    ী
    0.52
    സ
    0.51
     file
    0.49
     beide
    0.49
    ját
    0.47
     représ
    0.46
     préférences
    0.46
    ځ
    0.46
     தேர்த
    0.46
    POSITIVE LOGITS
    lic
    0.45
     साधारण
    0.45
    /%
    0.43
    ise
    0.43
    thin
    0.42
    skinned
    0.41
    icha
    0.40
    izh
    0.40
    util
    0.40
    wrapped
    0.40
    Activations Density 0.000%

    No Known Activations