© 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. 240551
    Prev
    Next
    INDEX
    Explanations

    HSA plans, explored Mars, all claims

    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
     influencing
    0.55
     article
    0.55
     influence
    0.53
    influence
    0.52
    Influ
    0.50
    ਰ
    0.50
     influences
    0.50
    Argument
    0.49
     gown
    0.49
     influencers
    0.48
    POSITIVE LOGITS
     Fie
    0.45
     Chương
    0.43
     제시
    0.43
    inizi
    0.42
    ђа
    0.42
     erwart
    0.41
     Entretanto
    0.41
    ινή
    0.41
    乾隆
    0.41
    汾
    0.41
    Activations Density 0.000%

    No Known Activations