© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23373
    Prev
    Next
    INDEX
    Explanations

    SIP and voice communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    光谱
    0.42
     spinal
    0.39
    毬
    0.39
    ছা
    0.39
     Expt
    0.39
     Lorena
    0.38
     mug
    0.38
    懒
    0.38
     cats
    0.37
     sucr
    0.37
    POSITIVE LOGITS
     SIP
    1.30
    SIP
    1.28
     sip
    1.19
     VoIP
    1.17
    sip
    1.11
     Sip
    1.05
     voicemail
    0.98
    Vo
    0.97
     telephony
    0.96
    Voice
    0.93
    Activations Density 0.027%

    No Known Activations