© 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. 217384
    Prev
    Next
    INDEX
    Explanations

    under terms and conditions

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

    underneath, within, under

    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
     STORIES
    0.44
    esz
    0.42
    э
    0.42
    newdata
    0.41
     EXTRA
    0.41
    urls
    0.40
     MUSE
    0.40
    ó
    0.40
    museum
    0.40
    elled
    0.40
    POSITIVE LOGITS
     بیماری
    0.55
    Limitations
    0.52
    讵
    0.50
     limites
    0.48
    PerTrial
    0.47
     aritmética
    0.47
    Limite
    0.47
     درجہ
    0.46
     данной
    0.46
    玑
    0.46
    Activations Density 0.000%

    No Known Activations