© 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. 137414
    Prev
    Next
    INDEX
    Explanations

    produced or assisted progression

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

    lasting durations

    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
     Dimension
    0.47
    김포
    0.47
    ஃப்
    0.45
    Trim
    0.45
    Mini
    0.44
     アルミ
    0.44
    ও
    0.44
    irittura
    0.44
    বী
    0.44
    ል
    0.44
    POSITIVE LOGITS
     lasting
    0.49
    lasting
    0.48
     lasted
    0.46
     FGD
    0.43
     lasts
    0.42
     Perman
    0.42
     तट
    0.41
     Ris
    0.41
     وقال
    0.41
     돼
    0.41
    Activations Density 0.000%

    No Known Activations