© 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. 40752
    Prev
    Next
    INDEX
    Explanations

    again

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

    again

    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
    _
    0.94
    ä
    0.84
     grenades
    0.78
    ]
    0.74
     stallions
    0.73
    )
    0.73
    。
    0.72
    '
    0.71
    )…
    0.71
    :
    0.71
    POSITIVE LOGITS
    на
    1.36
    l
    1.05
    la
    1.00
    na
    0.98
    м
    0.98
    s
    0.97
    n
    0.95
    ne
    0.89
    ni
    0.86
    يريا
    0.85
    Activations Density 0.027%

    No Known Activations