© 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. 212962
    Prev
    Next
    INDEX
    Explanations

    costs associated with events

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

    however, followed by new clause

    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
     reclamation
    0.48
    )」
    0.47
    formData
    0.45
     econometric
    0.44
     ਹ
    0.43
     メ
    0.43
    應
    0.42
     鳥
    0.42
     embargo
    0.41
    ัก
    0.41
    POSITIVE LOGITS
    인이
    0.51
    인
    0.45
     Climb
    0.44
    ilish
    0.43
    曛
    0.43
     Clinical
    0.42
    şk
    0.42
     Profession
    0.42
     शिवाय
    0.42
    僧
    0.42
    Activations Density 0.000%

    No Known Activations