© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55686
    Prev
    Next
    INDEX
    Explanations

    many, multiple, everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    u
    0.61
    zess
    0.48
    zee
    0.47
    ített
    0.46
    PrefabAsset
    0.46
    ́u
    0.45
    Kings
    0.45
    arev
    0.45
    o
    0.45
    Genetic
    0.44
    POSITIVE LOGITS
     چیر
    0.46
     brainstorming
    0.46
     वार्ता
    0.46
     bilater
    0.44
     choppy
    0.44
    частли
    0.44
     egreg
    0.42
     warring
    0.42
     gaping
    0.42
     doubts
    0.41
    Activations Density 0.009%

    No Known Activations