© 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. 49158
    Prev
    Next
    INDEX
    Explanations

    toy weapons

    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
    4
    0.45
    0
    0.45
    5
    0.44
    3
    0.41
     Question
    0.40
    af
    0.39
    ht
    0.39
    els
    0.39
     M
    0.39
     eliminated
    0.39
    POSITIVE LOGITS
     melan
    0.47
    ＮＡＮＡ
    0.46
     neurom
    0.46
    犯罪
    0.45
     воспа
    0.43
     prudence
    0.42
     vaisseau
    0.42
    感覚
    0.41
    దారి
    0.41
    SIBILITY
    0.40
    Activations Density 0.000%

    No Known Activations