© 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. 138416
    Prev
    Next
    INDEX
    Explanations

    oldest rocks, heavily on, distant past

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

    expanding upon details

    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
    くれた
    0.48
     rodz
    0.45
    ྭ
    0.45
    一大
    0.43
    レンズ
    0.43
    ্জ
    0.43
    sorted
    0.43
     semelh
    0.43
    '){$
    0.43
     jedną
    0.42
    POSITIVE LOGITS
     Initiatives
    0.47
     Comments
    0.44
     Ấn
    0.44
     Utilization
    0.44
     Defense
    0.43
     Inf
    0.42
     Industry
    0.42
     Công
    0.42
     Zero
    0.42
    aco
    0.41
    Activations Density 0.002%

    No Known Activations