© 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. 131754
    Prev
    Next
    INDEX
    Explanations

    save cash, start of, deck sale

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

    generating points or decisions

    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
    ryw
    0.46
    divid
    0.45
    썼
    0.45
    ĩnh
    0.44
    여러분
    0.43
    が可能
    0.43
    ್ಯೂ
    0.42
    都可以
    0.42
    öhn
    0.42
    𝔼
    0.42
    POSITIVE LOGITS
     ∀
    0.49
     ២
    0.48
     roadmap
    0.47
     GUT
    0.47
     gis
    0.46
     idha
    0.45
     SIL
    0.45
     بیٹ
    0.44
     GES
    0.44
     gutt
    0.44
    Activations Density 0.001%

    No Known Activations