© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 93453
    Prev
    Next
    INDEX
    Explanations

    completeness, emotional resonance, foundations

    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
    plicates
    0.47
    🔹
    0.46
     इवनिंग
    0.46
    faces
    0.43
    points
    0.43
    án
    0.43
    íos
    0.43
    chips
    0.43
     Schild
    0.43
    tails
    0.43
    POSITIVE LOGITS
    ตก
    0.45
     леп
    0.44
     ต
    0.43
    朝着
    0.40
     dahulu
    0.40
    กร
    0.39
     түр
    0.39
     বৃহত্তম
    0.39
     widespread
    0.39
     който
    0.39
    Activations Density 0.000%

    No Known Activations