© 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. 57953
    Prev
    Next
    INDEX
    Explanations

    sub-word units and descriptions

    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
     europeo
    0.44
     europea
    0.42
     gloom
    0.41
     gloss
    0.40
     살
    0.40
     elettronica
    0.40
     encycl
    0.38
     ㅇ
    0.38
     undone
    0.38
     bleak
    0.38
    POSITIVE LOGITS
    aske
    0.48
    นี
    0.47
    unities
    0.44
    ks
    0.44
    ator
    0.43
    rase
    0.43
    ore
    0.42
    ase
    0.42
    astro
    0.42
    пример
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.