© 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. 88903
    Prev
    Next
    INDEX
    Explanations

    competitive rates and fishing

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

    source node to all other nodes

    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
     akhirnya
    0.45
    ज़
    0.45
     човек
    0.44
    簟
    0.44
    सरत
    0.44
    तो
    0.44
     मानव
    0.44
     člov
    0.44
    nish
    0.44
     नीचे
    0.43
    POSITIVE LOGITS
     unsere
    0.48
    repo
    0.48
    mdan
    0.48
     manifests
    0.46
    ütü
    0.46
     들
    0.45
     基
    0.45
    hao
    0.45
     sullen
    0.45
     realizzazione
    0.44
    Activations Density 0.001%

    No Known Activations