© 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. 160326
    Prev
    Next
    INDEX
    Explanations

    verb + following word

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

    introducing details or examples

    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
     своя
    0.44
     Insel
    0.43
     നിന്ന്
    0.42
    的
    0.42
     Swamp
    0.41
    于
    0.41
     Sohn
    0.39
    与此同时
    0.39
     좀
    0.39
     있을
    0.39
    POSITIVE LOGITS
     polyethylene
    0.52
    rą
    0.49
    limegreen
    0.46
     reconsideration
    0.45
     caoutchouc
    0.45
    :\\
    0.44
    rš
    0.43
    elian
    0.43
     wants
    0.43
    لیس
    0.42
    Activations Density 0.001%

    No Known Activations