© 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. 802
    Prev
    Next
    INDEX
    Explanations

    previous actions or states

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

    previous states

    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
    𝙥
    0.39
    将于
    0.38
    ளுக்கான
    0.34
    将在
    0.34
    ड़
    0.34
    మ్
    0.33
    வுகளை
    0.33
     násled
    0.33
    ଧ
    0.33
    ణు
    0.32
    POSITIVE LOGITS
     previous
    1.82
     предыду
    1.73
    previous
    1.70
     sebelumnya
    1.63
    Previous
    1.59
    之前的
    1.59
     tidligere
    1.58
    以前
    1.56
     سابقا
    1.53
     tidigare
    1.52
    Activations Density 0.527%

    No Known Activations