© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 10565
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation

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

    words before enumerations

    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_40_width_16k_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
    紝
    0.51
    <unused2168>
    0.43
    <unused2121>
    0.42
    <unused1732>
    0.40
    <unused979>
    0.40
    <unused285>
    0.39
    स्यों
    0.38
     gitu
    0.38
    ?,
    0.37
    <unused342>
    0.37
    POSITIVE LOGITS
    ):
    1.91
    ():
    1.82
    *:
    1.76
    ):
    1.71
    }$:
    1.66
     ():
    1.66
    $:
    1.65
    »:
    1.59
    )$:
    1.54
    }):
    1.53
    Activations Density 1.082%

    No Known Activations