© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38182
    Prev
    Next
    INDEX
    Explanations

    journal entry, proof techniques, vendor compatibility

    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_31_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
     service
    0.48
    service
    0.45
    ቂያ
    0.44
    ﺟ
    0.42
     Service
    0.42
     servizio
    0.40
     εξα
    0.40
     aj
    0.38
     bronze
    0.38
     ta
    0.38
    POSITIVE LOGITS
     tedes
    0.47
     sexually
    0.47
    묭
    0.46
     Almanya
    0.45
     сексуа
    0.45
    ༥
    0.44
     моно
    0.43
    лото
    0.43
    제목
    0.43
    스키
    0.43
    Activations Density 0.001%

    No Known Activations