© 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. 9266
    Prev
    Next
    INDEX
    Explanations

    impersonal fast, obvious prognostic, surprised buy

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

    jokes about paranoia

    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
    ₂,
    0.43
    0
    0.43
    derive
    0.43
    ),
    0.42
    geq
    0.42
    9
    0.41
     вследствие
    0.40
    2
    0.40
     regulatory
    0.40
    distributions
    0.40
    POSITIVE LOGITS
     bébé
    0.49
     بُک
    0.48
     sooo
    0.47
     soooo
    0.47
     fuego
    0.47
    你会
    0.46
     triste
    0.45
     친구
    0.44
     childish
    0.44
     hermoso
    0.44
    Activations Density 0.010%

    No Known Activations