© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8166
    Prev
    Next
    INDEX
    Explanations

    citations with numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    https
    1.05
    http
    0.85
     https
    0.79
     http
    0.62
    ⓶
    0.61
    bigsqcup
    0.57
    codetest
    0.56
    MIT
    0.54
    urlString
    0.54
    ①
    0.54
    POSITIVE LOGITS
     infiltr
    0.64
     land
    0.63
    ેલા
    0.60
     reform
    0.60
     banana
    0.59
     scares
    0.57
     robot
    0.57
     scare
    0.57
     enc
    0.57
     influencers
    0.57
    Activations Density 0.020%

    No Known Activations