© 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. 20876
    Prev
    Next
    INDEX
    Explanations

    suitable for

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

    suitable or important for

    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
    aji
    0.45
    esistenza
    0.39
     অদৃশ্য
    0.39
    rico
    0.39
    Describe
    0.38
    每一
    0.38
    触
    0.38
    GONE
    0.37
    断面
    0.37
     끝
    0.37
    POSITIVE LOGITS
    เหมาะ
    1.30
    适合
    1.26
     เหมาะ
    1.16
     eignet
    1.13
     geschikt
    1.05
     suitable
    1.05
    適合
    1.00
     cocok
    0.99
     Suitable
    0.96
    suitable
    0.95
    Activations Density 0.123%

    No Known Activations