© 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. 139259
    Prev
    Next
    INDEX
    Explanations

    investigation, quality, address, terrace, roofs

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

    immortality, movement, bike

    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
    espèces
    0.47
     noon
    0.46
     yüzden
    0.45
     Consensus
    0.41
     stolet
    0.41
     lyn
    0.40
    াক্তন
    0.40
    牷
    0.39
    켰
    0.39
     criou
    0.39
    POSITIVE LOGITS
    proliferation
    0.45
     proliferation
    0.42
    新年
    0.41
     বিছ
    0.41
    扑
    0.41
    iname
    0.40
    on
    0.39
     inac
    0.39
    stimulation
    0.39
    ever
    0.39
    Activations Density 0.001%

    No Known Activations