© 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. 174579
    Prev
    Next
    INDEX
    Explanations

    with followed by words

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

    sexual content, medical terms, specific narratives

    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
    𝕦
    0.48
    லூர்
    0.46
    side
    0.45
    рая
    0.44
    ខាង
    0.44
    屐
    0.44
    一边
    0.43
     doo
    0.43
    綃
    0.43
     Surround
    0.42
    POSITIVE LOGITS
     culp
    0.51
     inicialmente
    0.48
     שמ
    0.47
    ówczas
    0.46
     pén
    0.45
    ድር
    0.45
     שנ
    0.44
     contraband
    0.43
     originalmente
    0.42
     confessed
    0.42
    Activations Density 0.000%

    No Known Activations