© 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. 37462
    Prev
    Next
    INDEX
    Explanations

    except or including

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

    including or regardless

    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
     অনেকটাই
    0.47
    咉
    0.44
     waveform
    0.43
     scène
    0.42
     AGAIN
    0.41
    लाइड
    0.39
     igen
    0.39
    젼
    0.39
    겅
    0.38
     yine
    0.38
    POSITIVE LOGITS
     except
    1.01
    except
    0.97
     excepto
    0.94
     kecuali
    0.91
     including
    0.90
     Including
    0.88
     включая
    0.88
    Including
    0.88
    including
    0.88
     Except
    0.87
    Activations Density 0.115%

    No Known Activations