© 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. 31-GEMMASCOPE-2-RES-262K
    7. 54377
    Prev
    Next
    INDEX
    Explanations

    Immediate sustained Political Planning

    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
    also
    0.46
    驊
    0.44
    también
    0.42
    と
    0.42
    continues
    0.41
    한다
    0.41
    ığını
    0.40
    わない
    0.40
    ЕНИ
    0.40
    }+
    0.40
    POSITIVE LOGITS
     pastry
    0.57
     culinary
    0.53
     caregivers
    0.53
     patty
    0.52
     assorted
    0.52
     chocol
    0.50
     prayer
    0.49
     nutritional
    0.49
     food
    0.47
     chemotherapy
    0.47
    Activations Density 0.006%

    No Known Activations