© 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. 2313
    Prev
    Next
    INDEX
    Explanations

    common phrases following specific words

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

    end, decimal, short, single, self, annual, straw, human

    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
    9
    0.51
     keempat
    0.46
    8
    0.46
    7
    0.45
     நேற்று
    0.44
    three
    0.43
     மூன்று
    0.43
     fourth
    0.43
    4
    0.41
    下列
    0.41
    POSITIVE LOGITS
    לי
    0.47
     crappy
    0.46
     shenanigans
    0.46
    שי
    0.44
     γιατί
    0.42
    בו
    0.42
    лимпиа
    0.41
    噱
    0.41
     thugs
    0.40
    涜
    0.40
    Activations Density 0.190%

    No Known Activations