© 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. 47969
    Prev
    Next
    INDEX
    Explanations

    unreal or stupid things

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

    state and Russian movie 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
    ôs
    0.52
     ponownie
    0.51
     verwendeten
    0.50
    বসাই
    0.50
    λεσ
    0.49
    হইয়া
    0.49
    valmentaja
    0.48
    몄
    0.48
    ammens
    0.48
     worden
    0.48
    POSITIVE LOGITS
    )))
    0.72
     есть
    0.71
     вроде
    0.68
     как
    0.66
     вообще
    0.66
     а
    0.65
     тут
    0.64
     Би
    0.61
     страш
    0.61
     говорю
    0.61
    Activations Density 0.040%

    No Known Activations