© 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. 20305
    Prev
    Next
    INDEX
    Explanations

    toxicity, datasets, which state, capable of, other restaurant, grief at, targeting Linux, database

    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
    רו
    0.49
    ﻟ
    0.48
    飴
    0.44
     احنا
    0.44
    恵
    0.43
    után
    0.42
    ուն
    0.41
     عرصے
    0.41
    рого
    0.41
    ल्यानंतर
    0.40
    POSITIVE LOGITS
    ajn
    0.46
    :
    0.46
    ifs
    0.45
    }:
    0.44
    istors
    0.44
     Waiver
    0.44
     auraient
    0.44
     violence
    0.42
     squats
    0.40
    okens
    0.40
    Activations Density 0.000%

    No Known Activations