© 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. 202196
    Prev
    Next
    INDEX
    Explanations

    again, repeatedly, newly, anew

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

    Avoid, why, responsibility, very

    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
    ᡤ
    0.48
     ဗ
    0.43
     negotiations
    0.42
    ဗ
    0.42
     rearrangement
    0.41
     settlements
    0.41
     meters
    0.40
     bookings
    0.40
     constitutions
    0.40
    αν
    0.39
    POSITIVE LOGITS
     novamente
    0.52
     опять
    0.52
     nuevamente
    0.47
     ponownie
    0.46
    кета
    0.45
     ентите
    0.45
    又要
    0.45
    惦
    0.45
     மீண்டும்
    0.44
     குற்ற
    0.44
    Activations Density 0.000%

    No Known Activations