© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8684
    Prev
    Next
    INDEX
    Explanations

    hypothetical scenarios and dependency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
     rasgos
    3.09
     exposición
    2.96
    ер
    2.89
    bones
    2.75
    ट
    2.65
    ve
    2.61
     ponerse
    2.59
    ти
    2.59
    গ
    2.53
    त्मक
    2.49
    POSITIVE LOGITS
    hemeral
    2.76
    ীয়
    2.76
     Tayyip
    2.75
    Acer
    2.71
    clientWidth
    2.70
    ointment
    2.70
    ﺢ
    2.69
    ﻖ
    2.68
    िक
    2.64
    ীয়
    2.62
    Activations Density 0.163%

    No Known Activations