© 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. 225004
    Prev
    Next
    INDEX
    Explanations

    Roma game

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

    health, with, cuckolding, pepper, carried

    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
    obiles
    0.45
     allerdings
    0.45
     Gould
    0.44
     comment
    0.44
    avelength
    0.43
    riever
    0.42
     remarks
    0.42
    ӓ
    0.42
     окре
    0.41
    €.
    0.40
    POSITIVE LOGITS
    सुर
    0.59
    ש
    0.55
    雩
    0.53
    規劃
    0.53
    ג
    0.53
    ניה
    0.52
    そこに
    0.49
    तक
    0.49
    ראש
    0.48
    רו
    0.48
    Activations Density 0.000%

    No Known Activations