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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 2115
    Prev
    Next
    INDEX
    Explanations

    details related to technical explanations of complex systems.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    analysis and results

    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_65k_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
     ylab
    0.44
    ঃ
    0.42
    ：
    0.41
     ngunit
    0.40
     constitutive
    0.40
     ঃ
    0.40
    <unused2148>
    0.40
     festivities
    0.40
     edilen
    0.39
     poiché
    0.39
    POSITIVE LOGITS
    and
    0.45
    this
    0.45
     እንዲሁም
    0.44
     samt
    0.44
    !!!
    0.43
    และ
    0.43
     Außerdem
    0.43
     Essence
    0.42
    5
    0.42
     Soc
    0.42
    Activations Density 0.569%

    No Known Activations