© 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. 156903
    Prev
    Next
    INDEX
    Explanations

    January favourites and strategy affect

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

    why question

    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
    Parrocchia
    0.46
    रित
    0.45
    Davidson
    0.43
     komun
    0.41
     residencial
    0.41
     indiquant
    0.41
    นอน
    0.41
    }$
    0.41
     menopause
    0.41
    ković
    0.40
    POSITIVE LOGITS
    asign
    0.47
     மதிப்ப
    0.46
    ৩৯
    0.46
    myItem
    0.46
     প্রতীক
    0.46
    шек
    0.45
     drap
    0.45
    чете
    0.45
    UES
    0.45
    шой
    0.44
    Activations Density 0.000%

    No Known Activations