© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 60223
    Prev
    Next
    INDEX
    Explanations

    CdTe cells

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

    predicting or guessing

    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
    8
    0.64
    4
    0.61
    3
    0.60
    6
    0.56
    Mounted
    0.53
    :
    0.53
    Akt
    0.50
    7
    0.50
    9
    0.49
    Stabil
    0.48
    POSITIVE LOGITS
     bárm
    0.56
     sketched
    0.55
     configurable
    0.51
     tüm
    0.51
     mécanismes
    0.49
     wszystkich
    0.49
     watched
    0.49
     všech
    0.47
     swept
    0.47
     düşünü
    0.46
    Activations Density 0.000%

    No Known Activations