© 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. 182250
    Prev
    Next
    INDEX
    Explanations

    group analyses

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

    evaluative descriptors

    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
     المدرسة
    0.46
    Dynamics
    0.45
    WT
    0.44
    urbance
    0.43
    粨
    0.43
     capacitances
    0.42
     permanece
    0.42
    Charting
    0.42
    艨
    0.41
     cercana
    0.41
    POSITIVE LOGITS
     misguided
    0.57
     prized
    0.53
     murderous
    0.53
     regretted
    0.52
     wasteful
    0.52
     justifiable
    0.50
     overrated
    0.50
     cheapest
    0.50
     persuasive
    0.49
     shabby
    0.48
    Activations Density 0.004%

    No Known Activations