© 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. 75063
    Prev
    Next
    INDEX
    Explanations

    osis Page, structures give, pros definitely, resources has, tiles game

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

    bonus points if you can

    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
     específica
    0.54
     específicos
    0.52
     আশে
    0.47
    हालय
    0.46
     Oğ
    0.46
    𒆜
    0.46
     Barrio
    0.46
     निवार
    0.45
    𝘇
    0.45
     Precinct
    0.45
    POSITIVE LOGITS
     vk
    0.53
    n
    0.50
     p
    0.44
     n
    0.44
     gad
    0.42
    -
    0.41
     mineral
    0.41
     scanned
    0.41
     vitamine
    0.40
    VK
    0.40
    Activations Density 0.000%

    No Known Activations