© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3660
    Prev
    Next
    INDEX
    Explanations

    allen keys, decryption keys

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

    key

    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_53_width_65k_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
     বসব
    0.41
    笾
    0.39
    azard
    0.38
    ้วน
    0.36
    逦
    0.35
    цам
    0.34
     পদার্থের
    0.34
    सर्ग
    0.34
    ढे
    0.33
    <unused76>
    0.33
    POSITIVE LOGITS
     key
    4.66
     Key
    4.34
    key
    4.31
     KEY
    4.28
     keys
    4.22
     клю
    4.19
    KEY
    4.13
    Key
    4.09
    キー
    4.09
     ключ
    3.89
    Activations Density 0.383%

    No Known Activations